This study addresses critical gaps in financial risk assessment and portfolio optimization by integrating advanced machine learning (ML) and deep learning (DL) techniques to handle the complexities of non-linearity, non-normality, and dynamic correlations among financial assets. This study comprehensively analyzes various dimensionality reduction techniques across different financial assets and time periods. By extracting non-linear features and constructing dynamic, data-driven covariance matrices, both linear and non-linear interactions among assets have been captured. This novel methodology hybridizes ML/DL and statistical approaches to enhance the robustness and resilience of portfolio optimization. The findings demonstrate significant improvements in profitability and stability under varying market conditions, offering a substantial advancement over prior studies. Therefore, this research provides a pioneering framework for more accurate and dynamic financial analysis, setting a novel standard in this research direction.

This study assesses the Large Language Models (LLMs) in creating investment portfolios. We implement a few-shot learning technique, followed by Retrieval Augmented Generation (RAG) enhanced with comprehensive up-to-date financial data, using Meta's latest LLM, Llama 3.1-8b. In the first phase, We assess the models' efficacy using key financial indicators, including total returns, annualized volatility, riskadjusted performance (Sharpe ratio), potential loss estimates (value-at-risk), and their pre-training knowledge with the S&P 500 Index performance baseline. In the second phase, we enhance the LLM's knowledge base by RAG and the latest historical and statistical metrics (such as earnings per share (EPS), dividends per share (DPS), profit margin, and many more) for each asset from different classes. The study constrains model inputs to specific sets of financial assets, such as equities, exchangetraded funds (ETFs), commodities, cryptocurrencies, and bonds. To evaluate model performance and adaptability, we analyzed across two distinct time frames: (1) within the models' training data cutoff, and (2) from the cutoff date to the present. This approach enables the assessment of model generalization to past and present market conditions. The research quantifies LLMs’ capabilities in financial asset allocation, comparing baseline performance against RAG-augmented strategies. Our results demonstrate that RAG-enhanced LLM significantly outperforms vanilla LLM in portfolio construction across various asset classes. We contemplate that these results could influence AI-driven financial decision-making processes such as automated trading, real-time sentiment analysis, and investment management.

Forecasting financial asset prices and quantifying associated risks are critical challenges in computational finance. This paper presents an optimal forecast combination framework by integrating advanced time series models and machine learning techniques to enhance prediction accuracy and risk assessment. A novel data-driven risk measure (DDRisknew) based on price differences is introduced, and sign correlation is used to capture risk and mitigate the limitations of traditional risk metrics. Our approach incorporates state-of-the-art forecasting models, including ARIMA, Neural Network Autoregressive, Long Short-Term Memory, XGBoost, and Random Forest, alongside two combination methods: equally weighted averages (FComp_SA) and datadriven optimal weighted averages (FComp_Weighted). Experimental results conducted on a dataset of stocks from ten diverse sectors during the highly volatile COVID-19 period demonstrate the superior performance of FComp_Weighted in minimizing forecasting errors across multiple metrics (RMSE, MAE, MAPE). Moreover, the RMSE of asset price and DDRisknewforecasts using FComp_Weighted models is always lower than the RMSE obtained using the FComp_SA model. This study underscores the importance of combining forecasts and provides a robust, computationally efficient framework for predictive modeling in financial markets. These findings have implications for algorithmic trading, portfolio optimization, and risk management, paving the way for future applications in broader domains like energy and cryptocurrency markets.

Contemporary information technology applications are overwhelmed by big data and require advanced data science analytics for careful investigation, interpretation, and predictions. Data sets in various applications exhibit high frequency with non-linear dynamic variability, and hence, leveraging the strengths of data-driven feature selection and sophisticated machine learning architectures becomes essential.This study proposes two novel architectures- Data-Driven Long Short-Term Memory (DD-LSTM) and Data-Driven Gated Recurrent Unit (DD-GRU), to improve predictive accuracy for highly fluctuating time-series data. Input data are log-transformed and used to derive data-driven risk forecasts and non-linear residuals based on underlying statistical features, which are then integrated with normalized original data into hyperparameter-optimized LSTM and GRU models. Experimental results with a financial dataset show that the proposed frameworks significantly outperform conventional LSTM and GRU by capturing intricate temporal patterns and risk dynamics. DD-GRU, in particular, exhibits greater computational efficiency, making it a robust solution for modeling nonlinear and irregular time-series data. This research not only addresses the critical challenge of optimizing temporal feature selection in high-frequency datasets but also offers a robust framework for analyzing complex temporal patterns across diverse high-frequency data sources.

Forecasting stock market indices is a challenging task due to the inherent complexity, non-linearity, and stochastic nature of financial time series. Although deep learning models, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures, outperform traditional econometric methods in capturing temporal dependencies, their standalone implementations often lack robustness and generalizability. This study presents a novel hybrid framework combining recurrent neural networks with Support Vector Regression (SVR) to address these limitations. The proposed approach integrates the sequential learning capabilities of LSTM and GRU with the nonlinear regression strengths of SVR, achieving superior predictive performance across diverse global indices. Empirical results highlight significant improvements over baseline models in both accuracy and adaptability to varying market conditions. The hybrid framework demonstrates its effectiveness in merging the advantages of its components, providing robust, generalizable predictions with reduced susceptibility to overfitting. These findings pave the way for future research in hybrid financial forecasting methods and their practical applications.

This study investigates data-driven financial correlation networks with a particular focus on modeling log returns using a data-driven t-distribution. A key contribution is showing that the covariance matrix of absolute log returns, used in volatility networks can be expressed as a function of the sign correlation and the covariance matrix of log returns. Fuzzy adjacency matrices are introduced to account for the uncertainty inherent in correlation estimates that depend on the degrees of freedom. Using data from 55 stocks across 13 sectors and S&P500 (big data), we compare four different networks based on correlations of log returns, volatility of log returns, data-driven volatility of log returns and sign(±) of returns. Three dynamic networks based on price correlations, ARIMA innovation correlations of the price and neuro innovation correlations of the price are also considered. All seven networks are evaluated using metrics such as average node degree, sparsity, and maximum eigenvalue. Unlike the existing work, the novelty of this study is demonstrating a relationship between data driven volatility networks and recently proposed volatility correlation networks without using distributional properties. Three different community detection algorithms demonstrate that the proposed data-driven volatility network proposed in this paper has a higher modularity score.

The eigenvalues of data-driven exponentially weighted moving average (DDEWMA) covariance matrix of stock returns plays an important role in portfolio optimization. Moreover, the eigenvalues of the Laplacian matrix play a fundamental role in financial network analysis. The novelty of this paper is to apply Random Matrix Theory (RMT) to denoise three covariance matrices ( empirical covariance, neuro covariance and DDEWMA covariance). Simulation study shows that portfolio weights generated using RMT filtered empirical covariance matrices based on both normal and t-distributed returns are more resilient. The networks built from t-distributed returns are more resilient (fewer but stronger connections with smaller average degree of nodes) than the networks built from normally distributed returns. Unlike the existing work, the novelty of this paper is to first show that the superiority of the RMT-filtered DDEWMA covariance model in portfolio optimization and, then show that the networks built from t-distributed returns are more resilient.

Forecasting stock prices and volatility plays a crucial role in making better investment decisions. Recently, there has been a growing interest in studying the Forecast Linear Augmented Projection (FLAP) method for multivariate normally distributed time series to reduce the forecast error variance and mean squared error (MSE) of long-term forecasts. FLAP method consists of three steps: formation of principal components, forecasting original and component series (base forecasts), and then projecting those base forecasts. First, this paper shows that the non-linear prediction (conditional mean) has a smaller MSE than the linear prediction. Then, it demonstrates that for multivariate time series, forecasts using the neural network autoregressive (NNAR) model with FLAP outperform those obtained by the commonly used autoregressive integrated moving average (ARIMA) model forecasts with FLAP (resulting in lower out-of-sample root mean squared error (RMSE) in general). For simulated multivariate data with t-distributed errors, the combined forecast model with NNAR and FLAP outperforms the NNAR forecast model. In the empirical study, we forecast stock price and volatility for 55 most traded stocks and S&P500 index using the ARIMA model with FLAP and the NNAR model with FLAP. The results show that FLAP is more effective in reducing forecast error variance and RMSE for non-stationary multivariate price and volatility forecasts.

Recently, there has been a growing interest in studying both long-term and short-term forecasts of electricity demand using dynamic regression models with seasonal ARIMA (SARIMA) errors and neural network autoregression (NNAR) models. Most of the electricity demand forecasting models investigated in the literature involved two features: temperature and day type, and only the point forecasts of temperature are used to obtain forecasts of electricity demand. However, it is crucial to acknowledge that temperature fluctuates throughout the day, and it is more appropriate to incorporate the forecast error variability and use the fuzzy forecasts of the temperature as an input to forecast electricity demand. This paper uses a novel fuzzy two-step approach to generate fuzzy forecasts of electricity demand. In step 1, fuzzy forecasts of temperature are obtained by incorporating additional features such as precipitation, irradiance, snowfall, snow mass, cloud cover, and air density. Thirteen distinct models, including neural network regression models and Facebook industrial Prophet models, are fitted to temperature data, and the best forecasting model for temperature is selected based on forecast accuracy measures. In step 2, the fuzzy forecasts of the temperature are used as a feature with day type (weekday/weekend/holiday) to obtain fuzzy forecasts of electricity demand. The superior performance of neural network fuzzy forecasts of electricity demand in terms of forecast accuracy is demonstrated for Ontario electricity demand data.

Recently, there has been a growing interest in using neuro volatility models in fuzzy forecasting and fuzzy option pricing. Neuro volatility models are used to model and predict financial market volatility by extending the neural network autoregressive (NNAR) model for nonlinear nonstationary times series data. In financial risk forecasting, various risk forecasting models for volatility are used to obtain the volatility forecasts, and the model risk ratio based on all the models is calculated to assess the stability of the financial system. However, the recently proposed neuro volatility models (based on neural networks such as LSTM, NNAR, etc.) are not used in evaluating the model risk. In this paper, novel 'neuro model risk forecasts' are obtained by including recently proposed neuro volatility models, and the resiliency of the financial system is studied. Unlike the existing model risk ratio forecasting based on linear volatility models, the driving idea is to use more appropriate nonlinear nonstationary neuro volatility forecasting models to obtain the model risk forecasts. The proposed model risk forecasts in this paper have been evaluated through extensive experiments, and it is shown that the model risk ratio can effectively serve as a metric for assessing the resilience and stability of the targeted financial system.

Portfolio optimization (PO) difficulties entail deciding which assets to invest and allocating the weights in those assets in order to maximize overall return while minimizing overall risk at the same time. With an increase in the vast number of assets available to invest, the stock selection and optimal asset weight allocation becomes more complex. In recent studies, researchers have achieved better performance in asset selection and weight allocation to an extent using nature-inspired algorithms than traditional methods often at the cost of heavy computing power used in blending multiple methods, or considering a small pool of assets. In this study, we propose a novel heuristics, which we call synchronous set-based particle swarm optimization (SSBPSO), that performs a large scale stock selection and weight optimization to generate resilient portfolios from a large pool of assets. The portfolios are generated from the pool of stocks that are constituents of stock indexes and their performance is compared with the indexes itself. We used three stock indexes from around the world and generated portfolios using SSBPSO, the returns of portfolio generated outperform the stock indexes in terms of portfolio return.

Pairs trading and multiple trading strategies are types of market-neutral strategies to use a pair or a combination of stocks and other financial instruments with co-integration or co-movements to generate potential profits, which may not be affected by the direction of the overall market. Commonly used pairs and multiple trading strategies are constructed using the Kalman Filter (KF) to utilize mean reversion in nonstationary but co-integrated asset prices. In this paper, we propose novel resilient pairs trading and multiple trading strategies using the combination of the KF algorithm and the KF innovation volatility interval forecasts using neural networks. The proposed trading strategies are implemented and investigated using the hourly prices of Bitcoin, Ethereum and Bitcoin Cash in the bear market. Those crypto assets are selected because they move in the same direction in the long term and have high trading volumes. The experimental results reveal performance for the proposed trading strategies with the upper and lower trading intervals using KF innovation volatility interval forecasts superior to that of the trading strategies with upper and lower trading bands using KF innovation volatility point forecasts. The performance and robustness of the proposed trading strategies using a proper assumption of transaction costs have also been examined. The strategies using innovation volatility interval forecasts consistently generate higher profits and a more robust number of transactions with or without transaction costs than those using innovation volatility point forecasts.

For many Markov chains that arise in applications (health, finance, etc.), state spaces are huge, and existing matrix methods may not be practical or even not possible to implement. In the literature, the expected waiting time for Markov chain (with a smaller number of states) generated patterns are obtained by finding an appropriate pattern matrix and solving a set of linear equations. In this paper, a fuzzy transition probability (TP) matrix is introduced, and a data-driven fuzzy pattern mining algorithm is proposed for sequence data of any length. The proposed algorithm, which avoids the inversion of the pattern matrix, is applicable to Markov chains with huge state spaces. The proposed algorithm studies two examples involving DNA sequence data with 3954 base pairs and patterns generated by the log-returns of the stocks/cryptocurrencies. Expected weighting times are compared with the traditional matrix approach. Incorporating stochastic variation in the TP estimates through fuzzy matrices, the new approach provides an alternative path to produce$\alpha$-cuts for TP matrices. The main contribution of this paper is to fit an appropriate MC model to a given sequence data and use the proposed fuzzy pattern mining algorithm to obtain resilient probabilistic forecasts and expected waiting time to reach patterns of interest.

One of the recent developments in computational finance has been the rise in using graph-based approaches to analyse stock market dynamics systematically. In algo trading literature, stocks for pairs trading and multiple trading are commonly selected by using Engle Granger and Johansen co-integration tests. Identifying all pairs eligible for trading in large datasets, entails a significant computational burden. In this paper, price correlation-based dynamic networks and differenced price series-based correlation networks and their importance ranks are used to pre-select pairs for trading. Algorithmic trading profits using commonly used co-integration methods are compared with the profits made by proposed correlation-based financial networks. Unlike the existing work, the novelty of the paper is that it uses data-driven correlation-based financial network approach to propose a stock selection method for pairs trading. In this paper, profit per transaction is used to compare the trading strategies. The superiority of the financial network stock selection method is discussed as well in some detail.

Recently, there has been a growing interest in utilizing empirical correlations of log returns to examine financial network models for stock prices by representing stocks as nodes and their relationships as edges. In this paper, empirical cor-relation, data-driven correlation, and cosine similarity matrices are used to obtain adjacency matrices for connectedness. For a given number of nodes, the simplest Erdos and Rényi (ER) model can be obtained by fixing the number of stocks and estimating the probability for any two vertices to be connected by an edge. Unlike existing work, the driving idea in this paper is to estimate the probability with the median cross-correlation to construct the ER network for observed volatility. Moreover, to address the uncertainty associated with these estimates of connectedness, this study introduces data-driven non-linear adaptive symmetric fuzzy adjacency matrices. In the literature, a certain thresh-old is identified for a network considering its connectedness. In this study, threshold and fuzzy parameters for the corre-sponding minimally connected fuzzy networks are determined, revealing unique network structures and the most significant stocks/cryptocurrencies (nodes with the highest number of links). Furthermore, as an application of the suggested fuzzy networks, three clustering approaches, fuzzy network clustering, k-means clustering, and Sharpe ratio clustering, are applied followed by the PageRank algorithm to construct optimal portfolios. A comparison of the constructed portfolios suggests that the fuzzy networks and clustering techniques are capable of yielding high cumulative returns during the study period.

This paper explores the impact of second-layer solutions, particularly the Lightning Network (LN), on Bitcoin mining fees. The introduction of LN promises enhanced transaction efficiency by facilitating faster and more economical off-chain transactions. Such advancements, while beneficial for network scalability, pose potential challenges to miners’ fee revenues—especially from lower-value transactions.We propose a comprehensive framework to assess the ramifications of LN adoption on miners’ fee earnings, taking into account the shift of transactions to LN. This framework not only evaluates the direct negative effects on miners’ fees but also examines the broader implications for Bitcoin’s network value as LN adoption increases, user base expands, and transaction volume grows.Moreover, our framework introduce the potential of LN to on-board millions of new users, particularly through the adoption by Superhubs. This significant expansion in network participation is posited to elevate Bitcoin’s overall value, potentially offsetting the initial decrease in mining fees.

Constructing resilient portfolios is of crucial and utmost importance to investment management. This study compares traditional and data-driven models for building resilient portfolios and analyzes their performance for stocks (S&P 500) and highly volatile cryptocurrency markets. The study investigates the performance of traditional models, such as mean-variance and constrained optimization, and a recently proposed data-driven resilient portfolio optimization model for stocks. Moreover, the study analyzes these methods with evolving S&P CME bitcoin futures index and the Crypto20 index. These analyses highlight the need for further investigation into traditional and data-driven approaches for resilient portfolio optimization, including higher-order moments, particularly under varying market conditions. This study provides valuable insights for investors and portfolio managers aiming to build resilient portfolios that could be used in different market environments.

Recently there has been a growing interest in studying fuzzy option pricing using Monte Carlo (MC) methods for diffusion models. The traditional volatility estimator has a larger asymptotic variance. In this paper, data-driven neuro-volatility estimates with smaller variances are used to obtain direct volatility forecasts. Asymmetric nonlinear adaptive fuzzy numbers are used to address ambiguity and vagueness associated with volatility estimates. This study uses fuzzy set theory and data-driven volatility forecasts to study call option prices of the S&P 500 index. Four modeling approaches have been considered, Black-Scholes (BS) model, Monte Carlo option pricing with normal / t errors, and the Jump-Diffusion (JD) model. Fuzzy α-cuts of option prices are presented and discussed under different parameter values. Our experimental study suggests that the JD model predicts the call option price more accurately compared to BS, normal errors, and t errors using the volatility estimate obtained using the Bayesian approach.

There have been several studies in the literature discussing the profitability with various trading strategies. Two common strategies are pairs trading and momentum strategies. The momentum strategy aims to exploit the phenomenon of momentum, where securities that have performed well in the past are likely to continue performing well in the future. The concept behind a pairs trading of stocks is similar to the statistical idea of cointegration. The goal of pairs trading is to profit from the relative price movements of the two assets, rather than from the absolute price movements of either asset. This strategy is generally implemented using algorithmic trading techniques, and it is often used by traders and investors to take advantage of mispricing in the market. In this study we first compare these two strategies and implement them to study for their profitability. We considered two major cryptocurrencies (Bitcoin and Ethereum) for these two trading strategies and show that with daily price data, dual momentum strategy generates significantly better results than the pairs trading strategy.

Data-driven volatility models and neuro-volatility models have the potential to revolutionize the area of Computational Finance. Volatility measures the variation of a time series data, and thus it is also a driving factor for the risk forecasting of returns from investment in cryptocurrencies. A cryptocurrency is a decentralized medium of exchange that relies on cryptographic primitives to facilitate the trustless transfer of value between different parties. Instead of being physical money, cryptocurrency payments exist purely as digital entries on an online ledger called blockchain that describe specific transactions.Many commonly used risk forecasting models do not take into account the uncertainty associated with the volatility of an underlying asset to obtain the risk forecasts. Some tools from the fuzzy set theory can be incorporated into the forecasting models to account for this uncertainty. Interest in the use of hybrid models for fuzzy volatility forecasts is growing. However, a major drawback is that the fuzzy coefficient hybrid models used in fuzzy volatility forecasts are not data-driven. This paper uses fuzzy set theory with data-driven volatility and data-driven neuro-volatility forecasts to study the fuzzy risk forecasts. The study focuses on long-term volatility forecasts with daily price data while briefly exploring forecasting models with high-frequency (hourly) data as an avenue for future research. Simple yet effective models incorporating fuzziness to obtain fuzzy risk volatility forecasts and fuzzy VaR forecasts are presented. The key underlying idea, unlike the existing risk forecasting, is the use of a hybrid nonlinear adaptive fuzzy model for volatility.

The market focuses on the Cboe Volatility Index (VIX) or Fear Index, an option-implied forecast of 30 calendar-day realized volatility of S&P 500 returns derived from a cross-section of vanilla options. The VIX is determined using a formula that derives the market’s expectation of realized one-month standard deviation of returns backed out from the near-term call and put options on the S&P 500 index. Market participants such as traders, asset managers, and risk managers, keenly watch the VIX index, and are interested in achieving accurate intelligent probabilistic forecasts of the VIX, and also of the realized volatility of individual stocks. These volatility forecasts are useful to options traders placing bets on the future volatility of individual stocks. This paper examines models that only utilize past values of the VIX and document improvements in forecasting the VIX (and its volatility) over different horizons. The approaches include long short-term memory (LSTM) models, simple moving average methods, data-driven neuro volatility techniques, and industry models like Prophet. Uniquely, we propose a novel VIX price interval forecasting model. The driving idea, unlike the existing VIX price forecasting models, is that the proposed novel LSTM interval forecasting method trains two LSTMs to obtain price forecasts and the forecast error volatility forecasts. All the proposed forecasting methods also avoid model identification and estimation issues, especially for a series like the VIX which is non-stationary. We compare models and document which ones perform best for varied horizons.

The Bitcoin whitepaper [1] published in 2008 pro-posed a novel decentralized ledger, later called blockchain, which enabled multiple transacting parties to agree upon the shared state of the ledger without a trusted intermediary. Blockchain technology has been used to implement many decentralized payment systems, with the general term Cryptocurrency coined for the native unit of values. The launch of the Turing-complete Ethereum blockchain [2] in 2015 extended the scope of blockchain-based financial systems beyond cryptocurrencies. The suite of non-custodial financial solutions deployed as Smart Con-tracts over Turing-complete blockchains is broadly called Decentralized Finance (DeFi). These solutions have gained widespread popularity as investment vehicles in the last two years, with their total value locked (TVL) exceeding USD 100 Billion. This paper reviews the key financial services offered in DeFi and draws a parallel to the corresponding services in the centralized financial industry. Some technical and economic risks associated with the DeFi investments are also discussed in the paper. Most of the existing review papers on DeFi focus on some specific DeFi services, are theoretically inclined, and are intended for academics in computer science or economics. This paper, on the other hand, aims to give an overview of the current state of the DeFi ecosystem. We aim to keep this review lucid to make it accessible to a broader audience without compromising academic rigor. The intended audience for this paper includes anyone with a basic understanding of financial markets and blockchain systems. This work will be specifically helpful for investment professionals to understand the rapidly evolving ecosystem of DeFi services.

The forecasting problems in Computational Finance involve modelling the vagueness and imprecision inherent to the financial markets. Fuzzy set theory has a unique ability to quantitatively and qualitatively model and analyze such problems. Volatility forecasting plays an important role in financial risk management and in option pricing. Recently, there has been a growing interest in data-driven volatility models and neurovolatility models for risk forecasting of stocks and index funds. However, even these state-of-the-art models do not take into account the fuzzy volatility in their risk forecasts.Cryptocurrencies are a novel financial asset class based on the Blockchain technology. Cryptocurrencies have gained popularity among retail investors as a financial asset with high risks and high returns. The extremely volatile nature of cryptocurrencies (compared to traditional assets) makes forecasting their volatility more challenging. A simple algorithmic trading approach, Simple Moving Average (SMA) crossover strategy, is used to calculate the Algo returns. This paper provides fuzzy forecasts of the volatility of Algo returns using the data-driven Exponentially Weighted Moving Average (DD-EWMA) and neuro models for six major cryptocurrencies. We also compute and compare fuzzy volatility forecasts of four major tech stocks and Chicago Board Options Exchange’s (CBOE) volatility index (VIX) using DD-EWMA and neuro models. Our experimental results show that the data-driven models produce better forecasts for cryptocurrencies as compared to the neuro models, while for the regular stocks and indexes, no such definitive conclusion could be drawn.

Supply chain literature reveals that study of resilient supply chains and bullwhip effect (BE) have been receiving special attention during pandemic for supply chains with seasonal as well as nonseasonal demand components. The BE phenomenon has been detected in various industries and sectors, and causes multiple inefficiencies such as higher costs of producing more than needed, wastage and transportation costs. As a result, BE forecast is of great importance for academics and supply chain managers. Despite the multitude of studies that have emerged addressing this issue, the impact of the quality of dynamic forecasts on the BE has received limited coverage in the literature. Optimal dynamic forecasts of the demand could allow managers to mitigate the upstream amplification of orders (and thus the BE), as well as reduce unnecessary inventory costs. Order quantity and BE in a supply chain depend on the forecast of the future demand. Usually minimum mean square error (MMSE) forecasts of the future demand are obtained by fitting an appropriate seasonal auto-regressive moving average (ARMA) time series model. However, a major drawback of the MMSE forecasting method is that it does not provide the associated risk forecasts. In this paper, a simple yet effective machine learning demand forecasting approach without fitting any time series model is presented.Specifically, a novel data driven machine learning algorithm that bypasses traditional forecasting steps and allows forecast weights to be optimized by minimizing the one-step ahead forecast error sum of squares (FESS) is proposed. A novel stability metric of a supply chain is proposed as the risk adjusted forecast of the future demand. It is shown that the risk adjusted forecasts can be used to check whether a given supply chain is resilient. In order to be more resilient and competitive in the current market, business leaders around the world agree that it is necessary to modernize and make major changes to their supply chain strategies. Demand risk forecasts obtained by the proposed machine learning approach allow supply chain managers to enhance the forecasting power of the order quantity and construct more resilient supply chains. The performance of proposed approach is evaluated through numerical experiments using simulated data and weekly demand data of two products. The results show that the performance of the proposed forecasts and risk adjusted forecasts of the future demand are better than the commonly used MMSE forecasts of the future demand.

Algorithmic trading uses a computer program that follows a defined set of instructions (an algorithm) to place a trade and can generate profits at a speed and frequency that is impossible for a human trader. Current state-of-the-art in algorithmic trading uses Kalman filtering (KF) and maximum informative resilient filtering (MIRF) that allow traders to enhance the predictive power of statistical models and improve trading strategies. There has been a growing interest in using MIRF in pairs trading, and a major drawback is that a threshold value (assumed to be one) is selected in an ad hoc way rather than maximizing the Sharpe ratio. In this paper, a novel random weights innovation volatility forecasting (RWIVF) algorithm is introduced to obtain the optimal data-driven weights of past observed volatilities instead of the equal weights by extending the Bollinger bands algo-tradinng strategy. RWIVF algorithm is also compared with the commonly used KF algorithm. Autocorrelations of the absolute values of the innovations in multiple trading are used to demonstrate that the innovations are non-normal with time-varying volatility. Performance of the RWIVF algorithm is shown using the experiments on cointegrated exchange-traded funds (ETFs). Analyses also explain how our approach can improve the performance of the trading strategies. The proposed novel resilient (robustness to initial values) trading strategies to the volatile stock market are also discussed in some detail.

There has been a growing interest in studying risk forecasting using data-driven exponential weighted moving average (DD-EWMA) volatility models as well as nonlinear neuro volatility models based on Neural network (NN). However, the recently proposed volatility forecasting models have not been used to study portfolio optimization. Large kurtosis of the portfolio return sequence shows that it follows a heavy-tailed t distribution. Significant sample autocorrelations of the absolute portfolio returns and squared portfolio returns suggest that time-varying volatility models are more appropriate to model the volatility. In this paper, a DD-EWMA portfolio volatility forecasting model is used to study the generalized portfolio optimization using the intelligent probabilistic risk forecasts based on data-driven t distribution of the portfolio returns. Optimal portfolio weights are obtained by minimizing the corresponding risk forecasts of portfolio volatility, mean absolute deviation (MAD), Value-at-Risk (VaR), and conditional Value-at-Risk (CVaR) for minimum risk forecast portfolios. Moreover the portfolio weights of the generalized tangency portfolios with different risk measures are obtained by maximizing the corresponding portfolio Sharpe ratio (PSR) forecasts. Experiments are conducted to show that the DD-EWMA volatility forecasting model is most computationally efficient (less computing time), whereas neuro volatility model takes longer time to obtain one-step ahead portfolio volatility forecasts. Moreover, the superiority of the portfolio selection based on data-driven volatility forecasts over the portfolio selection based on volatility estimates is demonstrated through numerical experiments using ten frequently traded stocks.

Portfolio risk management is an important success factor in an organization’s ability to deliver more business value. Moreover, constructing a true resilient portfolio is impossible without the inclusion of higher-order moments such as skewness and kurtosis. Recently there has been a growing interest in using machine learning methods with empirical variance covariance matrix of returns to study Markowitz portfolio optimization. A major drawback is that the tangency portfolios constructed by using the existing portfolio risk measures such as portfolio standard deviation, value-at-risk (VaR), conditional value-at-risk (CVaR), maximum absolute deviation (MAD) are always affected by the larger skewness and kurtosis of the portfolio return. This paper develops a set of metrics that extend the traditional portfolio Sharpe ratio (PSR) to measures that include skewness and kurtosis. Using a random portfolio approach, the paper demonstrates how to use these new metrics and optimize portfolios. Inclusion of higher moments such as skewness and kurtosis in portfolio risk management acknowledges the risk of asymmetric and heavy-tailed returns and can help in constructing resilient portfolios. For portfolio optimization, simple yet effective novel data-driven resilient portfolio risk measures incorporating skewness and kurtosis are presented in this paper. The results show that the performance of maximum mean-risk portfolios using the proposed portfolio risk measures based on volatility correlation and sign correlation outperform the commonly used tangency portfolio using portfolio standard deviation.

Recently, there has been a growing interest in portfolio optimization using graphical LASSO (GL) machine learning method, by assuming normality for asset returns. However, a major drawback is that most of the asset returns follow non-normal distributions and sample percentiles are used to study the portfolio optimization with Value-at-Risk (VaR) as a risk measure. In this paper, a data-driven random weights algorithm (RWA) and a sign correlation based portfolio return distribution are used to study the fuzzy portfolio optimization. The superiority of RWA over the commonly used genetic algorithm (GA) in computing the optimal portfolio weights is demonstrated by comparing the computing time. When comparing the estimate of the risk tolerance coefficient and the theoretical value for tangency portfolios with volatility as a risk measure, RWA outperforms (smaller absolute error) the GA. The novelty of this paper is the use of RWA and GA to calculate the fuzzy estimates (interval estimates) of the risk tolerance coefficient/optimal weights and using the sign correlation to obtain the data-driven distribution of the portfolio returns. More specifically the novelty is to obtain the fuzzy estimates of the risk tolerance coefficient and portfolio weights by modelling the portfolio volatility as an asymmetric triangular fuzzy number from the data-driven observed portfolio volatilities. In particular, the proposed RWA as well as GA lead to machine learning solutions for the portfolio optimization problems without a closed form solution and provide fuzzy estimates of the risk tolerance coefficient and the optimal portfolio weights.

Volatility forecasts and stock price forecasts play major roles in algorithmic trading. In this paper, joint forecasts of volatility and stock price are first obtained and then applied to algorithmic trading. Interval forecasts of stock prices are constructed using generalized double exponential smoothing (GDES) for stock price forecasts and data-driven exponentially weighted moving average (DD-EWMA) for volatility forecasts. Multi-stepahead interval forecasts for nonstationary stock price series are obtained. As an application, one-step-ahead interval forecasts are used to propose a novel dynamic data-driven algorithmic trading strategy. Commonly used simple moving average (SMA) crossover trading strategy and Bollinger bands trading strategy depend on unknown parameters (moving average window sizes) and the window sizes are usually chosen in an ad hoc fashion. However the proposed trading strategy does not depend on the window size, and is data-driven in the sense that the optimal smoothing constants of GDES and DD-EWMA are chosen from the data. In the proposed trading strategy, a training sample is used to tune the parameters: smoothing constant for GDES price forecasts, smoothing constant for DD-EWMA volatility forecasts, and the tuning parameter which maximizes Sharpe ratio (SR). A test sample is then used to compute cumulative profits to measure the out-of-sample trading performance using optimal tuning parameters. An empirical application on a set of widely traded stock indices shows that the proposed GDES interval forecast trading strategy is able to significantly outperform SMA and the buy and hold strategies for the majority of stock indices.

Many of the challenges and opportunities of data science in finance involve recursive smoothing, forecasting, filtering and pattern mining. Recently there has been a growing interest in using filtered estimates for dynamic hedge ratios for pairs trading. Moreover, rolling estimates and forecasts are used for pattern mining in technical analysis. Kalman filtering algorithms were successfully applied in pairs trading with only two co-integrated assets. In this paper, pairs trading strategy is extended to multiple trading (with more than two assets) strategy. Recently proposed non-Gaussian maximum informative filtering algorithms for dynamic state space models are used to obtain the filtered estimates of hedge ratios and applied in multiple trading. It is shown that the proposed multiple trading strategy outperforms (with higher profits) the commonly used pairs trading strategy using real data. A data-driven approach for selecting a parameter which maximizes the Sharpe ratio (SR) to generate optimal trading signals is also discussed in some detail.

Regularization methods allow data scientists and risk managers to enhance the predictive power of a statistical model and improve the quality of risk forecasts. Financial risk forecasting is about forecasting volatility, Value at Risk (VaR), expected shortfall (ES) and model risk ratio. While regularized estimates have been shown to perform well in model selection and parameter estimation, their applications in financial risk forecasting has not yet been studied. In this paper, regularized adaptive forecasts and computationally efficient forecasting algorithms for volatility, VaR, ES and model risk are studied using various regularization methods such as ridge, lasso and elastic net. Sample sign correlation of standardized log returns (standardized by volatility forecasts) is used to identify the conditional distribution of the log returns series and provide regularized interval forecasts as well as regularized probability forecasts. Superiority of the regularized risk forecasts is demonstrated using different volatility models including a recently proposed generalized data-driven volatility model in [8]. Validation of the regularized risk forecasts using real financial data is given. Regularized probabilistic forecasts for stationary time series models are also discussed in some detail.

Recently there has been a growing interest in using machine learning methods with empirical variance covariance matrix of returns to study Markovitz portfolio optimization. The statistical technique of graphical LASSO (GL) for stock selection in the portfolio assumes that the asset returns are normally distributed, independent random variables with constant variance. In this paper sign correlations and the autocorrelations of the absolute values of the returns are used to show that the returns are non-normal with time-varying volatility. We use the recently proposed data-driven exponentially weighted moving average (DDEWMA) volatility model to estimate the covariance matrix of asset returns in Markowitz portfolio optimization. Empirical results with big data (consists of 444 stocks for a period of 7 years downloaded from Yahoo Finance) show that the proposed DDEWMA variance covariance matrix model outperforms (larger Sharpe ratio) the model with empirical variance covariance matrix.

The explosion of algorithmic trading has been one of the most prominent trends in the finance industry. In this paper, two strategies for algorithmic trading such as Bollinger bands and the simple moving average (SMA) crossover strategy are studied in the fuzzy settings. The commonly used Bollinger bands trading strategy assumes that the difference between an asset's price and its SMA is normally distributed. However, it is shown that a data-driven t distribution is more appropriate to model the difference between an asset's price and its SMA. A novel data-driven fuzzy Bollinger bands strategy is proposed for algo trading. A good strategy should have a good algo return on investment with low algo volatility. Therefore, forecasting algo volatility and identifying an appropriate distribution of algo returns play a crucial role in algo trading. Sharpe Ratio (SR) is a measure of average algo return earned in excess of the risk-free rate per unit of algo volatility. For a class of SMA crossover strategies with varying window sizes, fuzzy estimates of SR are computed based on various risk measures including the data-driven volatility estimate (DDVE). SR fuzzy forecasts are computed using two recently proposed volatility forecasting models such as data-driven exponentially weighted moving average (DD-EWMA) and data-driven neuro volatility models. The main reason of using the fuzzy approach is to provide α-cuts (interval forecasts) of the SR. An empirical application on a set of widely traded technology stocks shows that the proposed models deliver forecasts of SR with small errors.

The ability to solve large-scale problems efficiently is one of the intrinsic values of a grid system. To maximize the throughput of the grid system, matching the submitted tasks to suitable resources is essential. This problem has been identified as the task matching problem. The task matching problem has been studied extensively in the past. Among other nature-inspired algorithms, Particle Swarm Optimization (PSO) has been used more commonly for the task matching problem and has shown promising results. Throughout the literature, the global PSO (gbest) has been chosen as the standard topology, while few other works have considered the local best (ring) topology for the task matching problem. As a result, there is a lack of research investigating the effectiveness of other topologies for the task matching problem. This knowledge gap has motivated our research to elucidate the impact of different PSO topologies on the task matching problem. We observed that the fully connected topology performed best (makespan) in many sets of experiments, but only slightly. Additionally, it was evident from the results that the pyramid topology achieved a slight edge over the other topologies in terms of makespan when all experiments were considered. However, each topology worked better on some problems and not as well on other problems. In addition, the population size significantly impacts the balance between the exploration and the exploitation search process.

Quantitative finance has been evolving over last several decades and combining randomness and fuzziness of the parameters has found growing interest among researchers to solve forecasting problems. Superiority of the fuzzy forecasting method over the minimum mean square forecasting had been demonstrated for fuzzy coefficient (linear as well as nonlinear) time series models in Thavaneswaran et al. [5]. However, many proposed fuzzy forecasting methods remain difficult to use in practice and there is a need for data-driven approach to fit the fuzzy coefficient volatility models. A neural network (NN) system can uniformly approximate any real nonlinear function on a compact domain to any degree of accuracy. Artificial NN (ANNs) have been applied to finance problems such as stock index prediction and bankruptcy prediction. In this paper, we introduce a novel direct data-driven neuro predictive model for conditional volatility and study the fuzzy value-at-risk (VaR) forecasts. We apply this model to forecast VaR with actual financial data. Our model shows considerable promise as a decision making and risk managing tool.

Recently there has been a growing interest in combining randomness and fuzziness to solve option pricing problems in finance using volatility models such as GARCH (generalized autoregressive conditional heteroskedasticity) and Heston-Nandi GARCH. The possibility theory for fuzzy option pricing (for real option, European option and binary option) has been demonstrated in the literature by fuzzifying the parameters such as volatility. However, many fuzzy option pricing approaches remain difficult to use with real data. A neural network (NN) is a highly parameterized model, widely promoted as a universal approximator such that with enough data it could learn any smooth predictive relationship. In this paper we first introduce a novel data-driven feed forward NN predictive model for conditional variance and demonstrate the superiority of the proposed model for option pricing over other volatility models. Using the NN predictive model, two different fuzzy estimates of the sensitivity measure vega (ν, which measures the dependence of option price on volatility σ) are proposed. We use different estimates of the sensitivity measure and compute the α-cuts of the fuzzy call price.

This paper introduces a modified genetic learning PSO (MGLPSO) algorithm for task matching problem in grid systems. MGLPSO incorporates genetic operators to create candidate solutions (exemplars) to guide the particles in the search space. Results show that MGLPSO is more efficient and effective in handling large-scale problem instances. Compared with PSO and Genetic Learning Particle Swarm Optimization (GLPSO), MGLPSO minimizes the makespan by 52% and 43%, respectively. Further, MGLPSO requires few iterations to obtain high quality solutions. Results also reveal that MGLPSO can achieve a good diversity while maintaining exploration and exploitation search.

In this paper, we introduce two ant based algorithms for the graph clustering problem. The first algorithm, Intelligent Ant Clustering (IAC), uses techniques such as hopping ants, relaxed drop function, ants with memories, and stagnation control as improvements to the original ant graph clustering algorithm AC-KLS by Kuntz et al. [1]. The second algorithm, Self Fixing Intelligent Ant Clustering (SFIAC), is inspired by polymorphic ant species such as the Pheidole genus [2]. In SFIAC, a second type of major ants (the foragers) is introduced to improve the global clustering quality in addition to the minor workers (the housekeepers) that run IAC locally. SFIAC outperforms or achieves the same modularity values as ACO-MMAS [3] and IAC on 7 out of 10 benchmark networks and is robust against different graphs. In practice, the speed of SFIAC is at least 10 times faster than MMAS, making it a comparatively scalable algorithm.

Summary High‐performance computing has witnessed the push towards computer hardware design in the past decade. Many real world problems are both data and compute intensive. Designing efficient algorithms is important to make effective use of the hardware resources for fast data analysis. Finance is one application that will benefit from these supercomputers. Options are instruments that give opportunity to profit from market movements without making large investments. However, understanding the asset price behavior and making a decision to enter into an option contract is quite challenging, called option pricing problem, because underlying asset price might vary violently. In this paper, we propose a nature‐inspired soft computing, meta‐heuristic, particle swarm optimization (PSO) algorithm to price options. We modify the PSO algorithm and incorporate varying volatility parameters to price options. The proposed algorithm, PSO with Varying Volatility (PSOwVV), is experimented with various PSO and financial parametric conditions. We also develop a parallel PSOwVV algorithm and implement on a distributed shared memory multi‐core machine. We show that the parallel algorithm performs well when the number of particles is linearly proportional to the number of processors. The parallel algorithm achieves a speedup of approximately 20× with 64 particles on a four node hybrid cluster. Copyright © 2014 John Wiley & Sons, Ltd.

Summary Recent work in metaheuristic algorithms has shown that solution quality may be improved by composing algorithms with orthogonal characteristics. At the same time, fused CPU‐GPU systems have emerged as a unique platform on which to study these algorithms. Using metaheuristic algorithms requires striking a balance between local and global exploration. There are no governing rules, however, to balance these. In this paper, we study two population‐based metaheuristic algorithms: multi‐swarm particle swarm optimization (MPSO) and genetic algorithms (GAs). We investigate parallel MPSO variants with genetic operators to increase quality: crossover, mutation, swapping, and all three. We develop a hybrid parallel algorithm that combines a slower convergent algorithm (GA) with a faster one (MPSO). The hybrid achieves significant initial improvement in solution quality but no significant difference in the final average fitness. Executing the GA on the GPU requires approximately an order of magnitude less time (0.07–0.18 s) than on the CPU. Our platform is the AMD A8‐3530MX accelerated processing unit that packs four ×86 CPU cores and 80 very long instruction word GPU processing elements. We make effective use of the hierarchical memory structure on the accelerated processing unit, four‐way very long instruction word vectorization, and zero‐copy buffers. Copyright © 2014 John Wiley & Sons, Ltd.

In Cloud computing, clients would like to pay fair price for the resources while providers would like to make profit for their services. In this study, we propose a Cloud Compute Commodity (C3) pricing architecture called Clabacus(Cloud-Abacus) to serve both parties. We use concepts and algorithms from financial option theory to develop Clabacus. We propose a general formula, called compound-Moores law, that captures the technological advances of the resources, rate of inflation and depreciation etc. We map these Cloud parameters to the option pricing parameters to effectively modify the option pricing algorithm in order to compute Cloud resource price. Using financial value-at-risk (VaR) analysis, we adjust the computed resource price to incorporate the inherent risks of the Cloud provider. We propose fuzzy logic and genetic algorithm based approaches to compute the VaR of the provider's resources. We have incorporated this into our Clabacus architecture. Finally, we study the effects of quality of service, rate of depreciation, rate of inflation, capital investment on the Cloud resource price for both client and provider. We show that if the prices are adjusted within a lower and upper bound, SLA can be guaranteed.

Special issue

Vehicular Ad hoc Networks (VANET) exhibit highly dynamic behavior with high mobility and random network topologies. The performance of Transmission Control Protocols (TCP) in such wireless ad hoc networks is plagued by a number of problems: frequent link failures, scalability, multi-hop data transmission and data loss. In this work, we make use of the vehicle's movement pattern, vehicle density, vehicle velocity and vehicle fading conditions to develop a hybrid, multi-path ant colony based routing algorithm, Mobility Aware Zone based Ant Colony Optimization Routing for VANET (MAZACORNET). that exhibits locality and scalability. We use ACO to find multiple routes between nodes in the network to aid in link failures. To achieve scalability we partition the network into multiple zones. We use proactive approach to find a route within a zone and reactive approach to find routes between zones using the local information stored in each zone thereby trying to reduce broadcasting and congestion. Our proposed algorithm makes effective use of the network bandwidth, is scalable and is robust to link failures. The results show that the algorithm works well for dense networks. The algorithm produces better delivery ratio and is scalable for zones beyond four. When compared to other existing VANET algorithms, the hybrid algorithm proved to be more efficient in terms of packet delivery ratio and end to end delay. To our knowledge this is the first ant based routing algorithm for VANET that uses the concept of zones.

The idea of utilizing nature inspired algorithms to find optimal solutions to various real world NP complete optimization problems has been extensively explored by researchers. One such problem is task matching problem in heterogeneous distributed computing environments like Grid and Cloud. Researchers have explored Swarm Intelligence algorithm, Particle Swarm Optimization (PSO), to find optimal solution for task matching problem. In this study, we investigate the effectiveness of smallest position value (SPV) technique in mapping continuous version of PSO algorithm to the task matching problem in a heterogeneous computing environment. We show that the task matching generated by this technique will result in in-efficient resource utilization. Thus, we present a novel load rebalance based particle swarm optimization heuristic (PSO-LR) for efficient load distribution among available compute nodes even in heterogeneous computing environments.

In this study, we design, develop, and simulate a cloud resources pricing model that satisfies two important constraints: the dynamic ability of the model to provide a high satisfaction guarantee measured as Quality of Service (QoS) - from users perspectives, profitability constraints - from the cloud service providers perspectives We employ financial option theory and treat the cloud resources as underlying assets to capture the realistic value of the cloud compute commodities (C3). We then price the cloud resources using our model. We discuss the results for four different metrics that we introduce to guarantee the quality of service and price as follows: (a) Moore's law based depreciation of asset values, (b) new technology based volatility measures in capturing price changes, (c) a new financial option pricing based model combining the above two concepts, and (d) the effect of age of resources and depreciation of cloud resource on QoS. We show that the cloud parameters can be mapped to financial economic model and we discuss the results of cloud compute commodity pricing for various parameters, such as the age of the resource, quality of service, and contract period.

Heterogeneous multi-core architectures have become an integral component of high performance systems and high performance scientific computing (HPC). The use of these systems has been vital for research applications but until recently have not been a factor in the consumer level experience. However, with new technologies such as AMD's Accelerated Processing Unit (APU) which combines the Central Processing Unit and Graphics Processing Unit onto a single die, consumers now have an affordable high performance system at their disposal. AMD's APUs are aimed at providing good performance and low power consumption for all markets. Financial applications can benefit from this heterogeneous architecture for real time processing. However, to obtain good performance, algorithms must be coded to efficiently utilize the APU architecture. In this paper, we have optimized two option pricing algorithms on the APU making use of vectorization and loop unrolling for improved performance. Our algorithms are tested on both an ATI Mobility Radeon 5870 and an AMD E-350 APU which use the VLIW5 architecture. We also study the power consumption of these architectures to determine how they compare to traditional CPU- and GPU- based systems.

Mathematical models like the Black-Scholes-Merton model used to price options approximately for simple and plain options in the form of closed form solution. The market is flooded with various styles of options, which are difficult to price. Numerical techniques used for pricing take exorbitant time for reasonable accuracy in pricing results. Heuristic approaches such as Particle swarm optimization (PSO) have been proposed for option pricing, which provide same or better results for simple options than that of numerical techniques at much less computational cost (time). In this work, we first investigate the characteristics of PSO for option pricing and propose improvements to PSO modeling, which reduces the number of PSO parameters without loss of generality of the financial application under study. We have used our improved PSO (called NPSO) model to price complex chooser option, one of the complicated options in the market. Cooperation among particles of the NPSO helps reach the solution in less time. Interest in diversifying investments stems from the necessity to avert risk involved in any single type of investments. The complex chooser option is shown to exhibit the characteristics of a financial portfolio. As a further study, we have used NPSO for portfolio optimization. We have implemented our NPSO model in the state-of-the-art multi-core Graphics processing units (GPU) platform and show that the computational time can be significantly reduced.

We investigate the performance of a highly parallel Particle Swarm Optimization (PSO) algorithm implemented on the GPU. In order to achieve this high degree of parallelism we implement a collaborative multi-swarm PSO algorithm on the GPU which relies on the use of many swarms rather than just one. We choose to apply our PSO algorithm against a real-world application: the task matching problem in a heterogeneous distributed computing environment. Due to the potential for large problem sizes with high dimensionality, the task matching problem proves to be very thorough in testing the GPUs capabilities for handling PSO. Our results show that the GPU offers a high degree of performance and achieves a maximum of 37 times speedup over a sequential implementation when the problem size in terms of tasks is large and many swarms are used.

Random numbers are used in a wide variety of applications from simulation and encryption to gambling and clinical trials. A good quality random number generator is an asset for applications like encryption, randomized designs and network and information security. Various mathematical models have been developed in the past to improve the quality of random numbers. It can be construed that in general to obtain random numbers of excellent quality, a complex mathematical model has to be used which can be a performance bottleneck. In this work, we propose a novel technique to implement a True Random Number Generator (TRNG) using sources of uncertainty found within Graphics Processing Units (GPUs) together with histogram equalization to obtain maximum entropy. We evaluate the random numbers generated by our approach using four tests. First, we measure the correlation values between two sequences of random numbers, second, we measure the entropy values, third, we use watermarking, an application used in network security and finally we use Monte Carlo analysis for pi-value calculation. Based on these quality measurements, our method has achieved better results than popular random number generators compared in this work. Furthermore, this approach is a massively scalable solution ideal for high performance computing implementations.

Cloud Federation is a recent paradigm that helps Infrastructure as a Service (IaaS) providers to overcome resource limitation during spikes in demand for Virtual Machines (VMs) by outsourcing requests to other federation members. IaaS providers also have the option of terminating spot VMs, i.e, cheaper VMs that can be canceled to free resources for more profitable VM requests. By both approaches, providers can expect to reject less profitable requests. For IaaS providers, pricing and profit are two important factors, in addition to maintaining a high Quality of Service (QoS) and utilization of their resources to remain in the business. For this, a clear understanding of the usage pattern, types of requests, and infrastructure costs are necessary while making decisions to terminate spot VMs, outsourcing or contributing to the federation. In this paper, we propose policies that help in the decision-making process to increase resources utilization and profit. Simulation results indicate that the proposed policies enhance the profit, utilization, and QoS (smaller number of rejected VM requests) in a Cloud federation environment.

In this paper, we apply the theory of financial option to design a model to price grid resources. We use GridSim, a grid simulation tool to simulate resource usage in a Grid. First, we integrate our pricing model to GridSim to price resources for the usage pattern generated randomly for a grid. Then, we price resources on six real grids for the resource usage trace data on these grids that we collected over a period of time.We introduce a new function called price variant function (pvf) in our model to adjust the charges for resources at various times so that the grid remains busy. We show that the pvf helps the resource provider in (1) keeping the grid busy and (2) recovering the investment on the infrastructure in a pre-determined period of time.

In recent years, Graphics Processing Units (GPUs) have been opened to general purpose programming. As a result, researchers and developers have access to the massively parallel GPU architecture for applications beyond that of graphics rendering and gaming. We first investigate a design and implementation of the trinomial lattice strategy for the pricing of simple European options on the GPU. This implementation serves to allow a comparison to be made to an existing, alternative implementation on the GPU. Following this introduction, we design an algorithm for pricing an exotic American look back option and analyze its pricing performance on the GPU. This look back option pricing algorithm showcases tremendous speedup over a sequential CPU implementation and hence suitable for real-time application.

The Graphics Processing Unit (GPU) is an asymmetric, heterogeneous multi-core architecture that can be used for high performance parallel computing applications. However, a significant level of interest has been focused on algorithms for solving regular problems, as these applications typically map well to the GPU. Irregular applications, which rely on pointer or graph-based data structures, have not been as extensively studied and are significantly more difficult to implement or map in an efficient fashion on the GPU. In this paper, we consider a graph-based maximum flow algorithm that has applications in network optimization problems. In the literature, the push-relabel maximum flow algorithm has been considered on the GPU. We believe that Malhotra, Pramodh Kumar and Maheshwari's algorithm is better suited for the GPU due to the synchronous, iterative nature of the algorithm. As a result, we choose this algorithm for our study. We show that the performance of the GPU algorithm far exceeds that of a sequential CPU algorithm.

Option pricing is one of the challenging problems in finance. Finding the best time to exercise an option is a even more challenging problem, especially since the price of the underlying assets change rapidly. In this work, we study complex path dependent options by exploiting and extending a novel idea that we proposed earlier using a nature inspired meta-heuristic algorithm. ant colony optimization (ACO). ACO has been used extensively in combinatorial optimization problems and recently in dynamic applications such as mobile ad-hoc networks where the objective is find a shortest path. However, in finance, especially in option pricing, we look for best time to exercise an option. Specifically, we use ants to decide on the best time to exercise so that the holder of the option contract will get the maximum benefit from his/her investment. Our algorithm and implementation suggests a better way to price options than traditional techniques such as Monte Carlo simulation or binomial lattice algorithm. Our pricing results compare very well with other techniques and at the same time the computational cost is reduced to a large extent.

Artificial neural networks are being widely used for time series forecasting. In recent years much effort has been made for the development of particle swarm algorithm for the optimization of neural networks. In this paper, the performance of two variants of particle swarm optimization algorithm (Trelea I and Trelea II) for training neural network has been examined with a real data for financial time series forecasting. Results clearly indicated the superiority of swarm based algorithms over the standard backpropagation training algorithm with respect to common performance measures across three forecasting horizons. In particular, with the Trelea II trained model, we obtained 92.48 %, 56.64 %, and 44.66 % decrease in terms of MSE over the standard back-propagation trained neural network for 10 days, 30 days and 60 days ahead forecasts respectively.

In this paper, we address a novel application of financial option pricing theory to the management of distributed computing resources. To achieve the set objective, first, we highlight the importance of finance models for the given problem and explain how option theory fits well to price the distributed grid compute resources. Second, we design and develop a pricing model and generate pricing results based on the trace data drawn from two real grids: one commercial grid Auvergrid and one experimental platform grid LCG. We evaluate our proposed model using various grid compute resources (such as memory, storage, software, and compute cycles) as individual commodities. By carrying out several experiments, a justification of the pricing model is obtained by comparing real behavior to a simulated system based on the spot price for the resources. We further enhanced our model to achieve a desirable balance between Quality of Service (QoS) and profitability from the perspectives of the users and resource operators respectively.

Estimating the current cost of an option by predicting the underlying asset prices is the most common methodology for pricing options. Pricing options has been a challenging problem for a long time due to unpredictability in market which gives rise to unpredictability in the option prices. Also the time when the options have to be exercised has to be determined to maximize the profits. This paper proposes an algorithm for predicting the time and price when the option can be exercised to gain expected profits. The proposed method is based on Nature inspired algorithm i.e. Ant Colony Optimization (ACO) which is used extensively in combinatorial optimization problems and dynamic applications such as mobile ad-hoc networks where the objective is to find the shortest path. In option pricing, the primary objective is to find the best node in terms of price and time that would bring expected profit to the investor. Ants traverse the solution space (asset price movements) in the market to identify a profitable node. We have designed and implemented an Aggregated ACO algorithm to price options which is distributed and robust. The initial results are encouraging and we are continuing this work further.

Mobile Ad Hoc Networks (MANETS) are infrastructureless network consisting of mobile nodes, with constantly changing topologies, that communicate via a wireless medium. Therefore, routing is a challenging issue in MANETs. Recently, nature inspired algorithms have been explored as means of finding an efficient solution to this routing problem. In this paper, we develop an improved routing algorithm for MANETs based on Ant Colony Optimization (ACO) inspired by real ants. The performance of the routing algorithm is evaluated through simulation and is compared to an existing well known MANET routing protocol, Ad hoc On-Demand Distance Vector (AODV). Several performance metrics are considered in different scenarios with varying mobility levels and traffic load.

Current research efforts in grid computing show that the available grid resources exist as non-storable compute cycles (grid compute commodities) and distributed geographically across dissimilar organizations with diverse resources usage polices. Therefore, guaranteeing grid resources availability as well as pricing them raises a number of challenging issues in several areas of computer applications. To guarantee QoS we propose a price-based, quality-aware model. We design and develop our model using the financial option theory from a real option perspective and value the grid resources by treating them as real assets. Our hybridized model combines both advantages of fuzzy logic reasoning and real options of a decision-based system. We have taken into account the fact that the grid resources availability depend on the time of use and are transient, and hence solutions from our model captures the realistic value of the grid resources and guarantees the certainty in the resources availability.

Summary form only given. Pricing of derivatives is one of the central problems in computational finance. Since the theory of derivative pricing is highly mathematical, numerical techniques such as binomial lattice, finite-differencing and fast Fourier transform (FFT) among others have been used for derivative or option pricing. Based on a recent work on FFT for VLSI circuits, we develop a parallel algorithm in the current work, which improves data locality and hence reduce communication overheads. Our main aim is to study the performance of this algorithm. Compared to the traditional butterfly network, the current algorithm with data swap network performs better by more than 15% for large data sizes.

Abstract This paper reports a study of sparse Matrix Vector Multiplication (MVM) on a parallel computing platform based on a fine‐grained multithreaded program execution model. Such sparse MVM computations, when parallelized without performing graph partitioning, suffers a very high communication to computation ratio, and is well known to have a very limited scalability on traditional distributed‐memory machines. The particular multithreaded system we use is the Efficient Architecture for Running THreads (EARTH) model, which can be implemented from off‐the‐shelf processors. With the Class B input sparse matrix from the NAS CG benchmark (75 000 rows), we attain an absolute speedup of 90 on 120 nodes of a distributed memory configuration. This is achieved without using inspector/executor or graph partitioning, or any communication minimization phase, which means that similar results can be expected for adaptive problems as well. High scalability is achieved because of a number of characteristics of the EARTH architecture: local synchronizations, low communication overheads, ability to overlap communication and computation, and low context‐switching costs. Copyright © 2002 John Wiley & Sons, Ltd.

In this paper, we study multithreaded algorithms for pricing American Style options. We describe the algorithms, explain their relative complexities, and study their performance. The binomial lattice problem has been formulated in two distinct ways. In the first approach, the recursive algorithm, we establish a parent-child relationship between threads while fully exploiting the inherent parallelism. The second approach, the iterative algorithm, follows a data-flow model based on the producer-consumer style of programming. We implement the algorithms on the EARTH platform. The limitations posed by the problem size on the recursive algorithm and the solution to overcome this problem by the iterative algorithm are explained through the performance results. We have then extended these algorithms to study complicated options with dividend paying underlying assets and reported the performance results.