This paper introduces LSTMGraph, a unified time-series model designed for demand prediction across multiple products. This method integrates Long Short-Term Memory (LSTM) networks to capture temporal dynamics, such as price fluctuations, and Graph Convolutional Networks (GCN) to model global dependencies between products. We represent demand data as a network where each product is a node, constructing three distinct graphs with different types of edges: (i) a weekly sales similarity graph, (ii) a customer-based relationship graph, and (iii) an invoice-based similarity graph. These graphs are merged to enhance predictive accuracy by incorporating diverse temporal and relational patterns. Extensive experiments show that LSTMGraph significantly outperforms existing baseline models. Additionally, an ablation study is conducted to quantify the impact of each graph type on overall performance.

Cryptocurrencies fluctuate in markets with high price volatility, which becomes a great challenge for investors. To aid investors in making informed decisions, systems predicting cryptocurrency market movements have been developed, commonly framed as feature-driven regression problems that focus solely on historical patterns favored by domain experts. However, these methods overlook three critical factors that significantly influence the cryptocurrency market dynamics: 1) the macro investing environment, reflected in major cryptocurrency fluctuations, which can affect investors collaborative behaviors, 2) overall market sentiment, heavily influenced by news, which impacts investors strategies, and 3) technical indicators, which offer insights into overbought or oversold conditions, momentum,and market trends are often ignored despite their relevance in shaping short-term price movements. In this paper, we propose a dual prediction mechanism that enables the model to forecast the next day’s closing price by incorporating macroeconomic fluctuations, technical indicators, and individual cryptocurrency price changes. Furthermore, we introduce a novel refinement mechanism that enhances the prediction through market sentimentbased rescaling and fusion. In experiments, the proposed model achieves state-of-the-art performance (SOTA), consistently outperforming ten comparison methods in most cases.

This study presents a multi-scale demographic analysis of COVID-19 booster vaccination rates using Graph Neural Networks (GNNs). Data from Nueces County, Texas, was analyzed at two levels of geographic granularity: block groups and census tracts. The block group model demonstrated superior accuracy in predicting vaccination rates compared to the census tract model, emphasizing the importance of fine-grained data for public health planning. To evaluate the combination of models at different scales, aggregation methods such as weighted sum, majority voting, and stacking were employed. While these methods provided insights, they did not outperform the block group model. The study highlights the potential of GNNs for improving public health interventions through targeted vaccination strategies. Limitations include the dataset's focus on data up to February 2022 and the absence of more granular demographic factors. Future work will incorporate temporal factors and explore smaller geographic scales, such as block-level data, for enhanced precision.

Forecasting citations of scientific patents and publications is a crucial task for understanding the evolution and development of technological domains and for foresight into emerging technologies. By construing citations as a time series, the task can be cast into the domain of temporal point processes. Most existing work on forecasting with temporal point processes, both conventional and neural network-based, only performs single-step forecasting. In citation forecasting, however, the more salient goal is n -step forecasting: predicting the arrival of the next n citations. In this article, we propose Dynamic Multi-Context Attention Networks (DMA-Nets), a novel deep learning sequence-to-sequence (Seq2Seq) model with a novel hierarchical dynamic attention mechanism for long-term citation forecasting. Extensive experiments on two real-world datasets demonstrate that the proposed model learns better representations of conditional dependencies over historical sequences compared to state-of-the-art counterparts and thus achieves significant performance for citation predictions.

For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being. To this end, we harness the power of social media data, a rich source of public sentiment, to enhance the accuracy of stock market predictions. Diverging from conventional methods, we pioneer an approach that integrates sentiment analysis, macroeconomic indicators, search engine data, and historical prices within a multi-attention deep learning model, masterfully decoding the complex patterns inherent in the data. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.

Predicting stock market is vital for investors and policymakers, acting as a barometer of the economic health. We leverage social media data, a potent source of public sentiment, in tandem with macroeconomic indicators as government-compiled statistics, to refine stock market predictions. However, prior research using tweet data for stock market prediction faces three challenges. First, the quality of tweets varies widely. While many are filled with noise and irrelevant details, only a few genuinely mirror the actual market scenario. Second, solely focusing on the historical data of a particular stock without considering its sector can lead to oversight. Stocks within the same industry often exhibit correlated price behaviors. Lastly, simply forecasting the direction of price movement without assessing its magnitude is of limited value, as the extent of the rise or fall truly determines profitability. In this paper, diverging from the conventional methods, we pioneer an ECON (A Framework Leveraging Tweets, Macroeconomic Indicators, and Historical Prices to Predict Stock Movement and Volatility). The framework has following advantages: First, ECON has an adept tweets filter that efficiently extracts and decodes the vast array of tweet data. Second, ECON discerns multi-level relationships among stocks, sectors, and macroeconomic factors through a self-aware mechanism in semantic space. Third, ECON offers enhanced accuracy in predicting substantial stock price fluctuations by capitalizing on stock price movement. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.

Predicting the impact of traffic i ncidents b ased on traffic s ensor d ata i s a n e ssential r esearch t opic i n t he fi eld of Intelligent Transportation Systems (ITS). Tackling the problem of estimating the durations of incidents from their early stages is a challenge due to the variable nature of such incidents and the complex structure of modern road networks. Existing studies on forecasting the incident duration from sensor data are mostly incapable of modeling 1) the spatiotemporal correlations of traffic s ensors a nd a rterial r oads a nd 2 ) t he hierarchical topology of the traffic sensor and road networks. In this paper, we propose the Hierarchical Attention-based Spatiotemporal Graph Convolutional Network model (HastGCN) to solve the incident duration forecasting problem by formulating the spatiotemporal correlation and traffic p atterns o n b oth t he s ensor l evel and the road level in their natural hierarchical manner. At the sensor level, we propose a spatiotemporal attention mechanism followed by graph convolutions to model the local correlations and patterns between traffic s ensors o n t he s ame a rterial road. At the road level, a connectivity-aware attention mechanism is designed to learn the global spatial relatedness between each arterial road. Traffic-condition a ware g raph c onvolutions are then applied to understand the target incident representation for the incident duration forecasting.

Cybersecurity event detection is a crucial problem for mitigating effects on various aspects of society. Social media has become a notable source of indicators for detection of diverse events. Though previous social media based strategies for cyber-security event detection focus on mining certain event-related words, the dynamic and evolving nature of online discourse limits the performance of these approaches. Further, because these are typically unsupervised or weakly supervised learning strategies, they do not perform well in an environment of biased samples, noisy context, and informal language which is routine for online, user-generated content. This paper takes a supervised learning approach by proposing a novel multi-task learning based model. Our model can handle diverse structures in feature space by learning models for different types of potential high-profile targets simultaneously. For parameter optimization, we develop an efficient algorithm based on the alternating direction method of multipliers. Through extensive experiments on a real world Twitter dataset, we demonstrate that our approach consistently outperforms existing methods at encoding and identifying cyber-security incidents.

Critical incident stages identification and reasonable prediction of traffic incident duration are essential in traffic incident management. In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. First, we formulate a sparsity optimization problem that extracts low-level temporal features based on traffic speed readings and then generalizes higher level features as phases of traffic incidents. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the spatial connectivity of the road network to predict the incident duration. The proposed problem is challenging to solve due to the orthogonality constraints, non-convexity objective, and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world traffic data and traffic incident records justify the efficacy of our model.

With the rapid growth in urban transit networks in recent years, detecting service disruptions in a timely manner is a problem of increased interest to service providers. Transit agencies are seeking to move beyond traditional customer questionnaires and manual service inspections to leveraging open source indicators like social media for deteting emerging transit events. In this paper, we leverage Twitter data for early detection of metro service disruptions. Inspired by the multi-task learning framework, we propose the Metro Disruption Detection Model, which captures the semantic similarity between transit lines in Twitter space. We propose novel constraints on feature semantic similarity exploiting prior knowledge about the spatial connectivity and shared tracks of the metro network. An algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed model. We run extensive experiments and comparisons to other models with real world Twitter data and transit disruption records from the Washington Metropolitan Area Transit Authority (WMATA) to justify the efficacy of our model.

Social media is often viewed as a sensor into various societal events such as disease outbreaks, protests, and elections. We describe the use of social media as a crowdsourced sensor to gain insight into ongoing cyber-attacks. Our approach detects a broad range of cyber-attacks (e.g., distributed denial of service (DDoS) attacks, data breaches, and account hijacking) in a weakly supervised manner using just a small set of seed event triggers and requires no training or labeled samples. A new query expansion strategy based on convolution kernels and dependency parses helps model semantic structure and aids in identifying key event characteristics. Through a large-scale analysis over Twitter, we demonstrate that our approach consistently identifies and encodes events, outperforming existing methods.