Real estate valuation is a complex process conditioned by real estate’s legal, economic, and social environment. Difficulties faced by the real estate appraiser in the valuation process become the reason for research and the creation of tools to support valuation. The purpose of this research is to investigate the applicability of machine learning methods in the real estate valuation process. The subject of the study was the investment land real estate market in Wroclaw. The time base of the research conducted is data on land real estate transactions in the period 2016-2022. A database was developed, which was used to verify the predictive capabilities of regression models, random forest and artificial neural network for a limited real estate market. The highest results in this study were achieved for the artificial neural network model, where the lowest prediction errors are at 13% MAPE.

Currently, primary residential real estate market is steadily increasing its prices regardless of the pandemic and national quarantine. There is great potential for financial gain and knowledge in the analysis of this market. Individual analysis seems difficult and time-consuming. This leads to the problem of estimating a favorable price for an apartment. Another example of the use of housing price prediction algorithms can be, for example, an agency engaged in finding, buying and selling properties. In order to maximize profits, the company can invest in an application that can estimate housing prices very accurately. This will reduce the likelihood of overpaying for an investment and give a sticking point for negotiations. In addition, a good price prediction will give you an edge in the real estate trade market. Knowing the value of the house will allow you to lower the price during purchase talks and then sell the apartment at the actual or higher price. The main aim of the paper is to develop a model and application for prediction of residential real estate price in Wroclaw primary market. Data Scraping approach, Simple Linear Regression, Gradient Boosting Regression, Multiple Linear Regression, LASSO, RandomForest Regression methods will be used for this research. In summary, the developed models and application for prediction of residential real estate price in Wroclaw primary market allows for achieving precision about 90%. Developed application can be used by companies that are considering starting this type of project and, for this purpose, are looking for an example of the entire process, starting with an idea and ending with a statistical model that predicts housing prices based on selected characteristics. The scraping application can be used for commercial as well as private purposes during market analysis. In addition, it can also serve as a basis for new solutions and ventures.

Abstract Trading decisions often encounter risk and uncertainty complexities, significantly influencing their overall performance. Recognizing the intricacies of this challenge, computational models within information systems have become essential to support and augment trading decisions. The paper introduces the concepts of trading software agents, investment strategies, and evaluation functions that automate the selection of the most suitable strategy in near real-time, offering the potential to enhance trading effectiveness. This approach holds the promise of significantly increasing the effectiveness of investments. The research also seeks to discern how changing market conditions influence the performance of these strategies, emphasizing that no single agent or strategy universally outperforms the rest. In summary, the overarching objective of this research is to contribute to the realm of financial decision-making by introducing a pragmatic platform and strategies tailored for traders, investors, and market participants in the FOREX market. Ultimately, this endeavor aims to empower people with more informed and productive trading decisions. The contributions of this work extend beyond the theoretical realm, demonstrating a commitment to address the practical challenges faced by traders and investors in real-time decision-making within the financial markets. This multidimensional approach to financial decision support promises to enhance investment effectiveness and contribute to the broader field of algorithmic trading.

The purpose of the research is to study the cryptocurrency data listed on Binance, and design a profitable strategy based on the findings. The data covers over 150 selected cryptocurrencies. The study aims to detect anomalies in the volume and number of transactions and apply an investment strategy based on deviations and sudden price fluctuations. An autoencoder and LSTM-based neural network have been used. Based on the results of the present research, it can be concluded that the model successfully identified anomalies in the data regarding the volume and number of transactions carried out. I it was also observed that price volatility in the period close to the detected anomaly was significantly higher than average volatility for the sample.

Integration of management information systems is crucial to optimizing internal and external processes in enterprises' environments. One of the technologies sup-porting this integration is OPC UA. An embedded automation device OPC UA server can transmit either dead-band tested analog attributes or all changes of ana-log attributes to OPC UA clients. Typically OPC UA server to OPC UA client data transmission is based on subscriptions. Subscription interval, sampling interval, and dead-band are usually controlled by OPC UA clients [1]. It is, however, desirable that OPC UA data traffic is controlled by automation de-vice control programs and the embedded OPC UA servers and not by OPC UA clients as specified in the norm. This is because the OPC UA server is the limiting component in the client sever communication scheme. Floating-point attributes in an automation device have small changes all the time, but in real-world plants, analog attributes do not necessarily have to be frequently communicated to OPC UA clients on small changes. In addition to an attribute dead-band test, changes in some attributes can safely be blocked a minimum time since the last attribute update before a new value is transmitted to the UA clients. Analog attributes can also be cyclically transmitted to OPC UA clients with a low frequency to ensure that they receive the exact attribute value after a set maximum time. This paper demonstrates an implementation of this communication scheme by using a device function block to control traffic between an OPC UA server and OPC UA clients for analog attributes.

The paper presents issues related to methods used in breast histopathological images tumor changes detection. The problem is connected with sustainable health issues which focus on the improvement of health and better delivery of healthcare, rather than late intervention in disease, with resulting benefits to patients and to the environment on which human health depends, thus serving to provide high quality healthcare. The main purpose of the paper is to develop a model based on deep artificial neural networks for the cancer detection in histopathological breast images. The implementation of the proposed model fits in with the concept of sustainable health through the support of the work of doctors in their decisions, diagnosis and in the reduction of the human workload and time, which can be referred to improve the health services. Data set contains 277524 samples from 163 breast histopathological images taken with the WSI scanner. The model is based on a convolutional neural network in the ResNet-18 architecture, which consists of residual blocks. During the final validation on the test set, the network achieved an accuracy of 93.6% and a 87.3% sensitivity in the detection of cancer tissues. The overall performance of the model is characterized by an F1-score of 0.887. The obtained results indicate the possibility of using the system in clinical conditions.

Data analysis is currently one the key for the success of good condition of the companies. Feature selection as a preprocessing of data method the estimator accuracy scores can be improved, as well the performance on very high-dimensional data set can be boosted. The paper presents an application of the filter Feature Selection method to check how the data set after the application of the selected method will look like. The goal of this article is to compare the feature selection method with the application without usage of Feature Selection about the set of prepared financial data. For this purpose, the experiments have been executed with usage of Jupyter Notebook with Python as a programming language. The data source for the data set was Stooq, which is an open source website for tracking of changes on the financial markets. For this purpose, several joint-stock companies of various sectors from Polish Stock Exchange have been selected. The Feature Selection has been applied before the data has been entered into the Artificial Neural Networks model. The results have been compared using the MSE value. The lowest MSE value has been obtained where no Feature Selection method has been applied, however MSE value for Filter Method is one order of magnitude smaller. For the experiments without Feature Selection 112 input variables have been used, for the Filter Method only 4 variables have been incorporated.

As a critical consideration in investment decisions, stock liquidity has significance for all stakeholders in the market. It also has implications for the stock market’s growth. Liquidity enables investors and issuers to meet their requirements regarding investment, financing or hedging, reducing investment costs and the cost of capital. The aim of this paper is to develop the machine learning models for liquidity prediction. The subject of research is the Vietnamese stock market, focusing on the recent years - from 2011 to 2019. Vietnamese stock market differs from developed markets and emerging markets. It is characterized by a limited number of transactions, which are also relatively small. The Multilayer Perceptron, Long-Short Term Memory and Linear Regression models have been developed. On the basis of the experimental results, it can be concluded that the LSTM model allows for prediction characterized by lowest value of MSE. The results of research can be used for developing the methods for decision support on stock markets.

One of the most common applications of neural networks itself is data prediction models, for example, future stock market prices, calculated based on historical data. Spiking neural networks are one of the emerging architectures showing great potential in solving complex problems in complicated information environments. However, to the best of our knowledge, the spiking neural networks have not been successfully applied in stock market data prediction. The values of exchange-traded funds (ETF), due to their flexibility and simplicity, can be a good application of such a tool. Therefore, the following article provides the results of a comprehensive experimental comparison of different spiking neural networks in predicting ETF values. The main goal was to check if the spiking neural networks obtain better or worse results of forecasting than traditional neural networks. The secondary goal was a comparison of different spiking neural network architectures between themselves to judge which one is the most applicable to the given problem

The production of food in an ecologically and economically sustainable manner is of significant importance today. Agricultural producers are increasingly being accompanied by elements of Agriculture 4.0 such as automation and decision-making support. This work shows an example of how the digitization of viticulture can be significantly supported by Deep Learning. The work presents an approach that can overcome the loss of human expertise in grape identification by using image-recognition-techniques and residual network architectures. Our developed model for grape identification at a vineyard reaches an accuracy of 99% of correctly recognized grape varieties.

Financial decision supporting is a very important and complex problem. The aim of this paper is to develop the Supervised Learning method based on the random forest algorithm for decision support on stock exchange. Contemporarily, machine learning methods, including decision trees, are often used. Many research works and practical implementation projects focus on supporting decisions on stock markets. However, most of them are related to developed markets in the USA or Western Europe, or Asian stock markets. There is a lack of research related, for example, to the Warsaw Stock Exchange (WSE). The findings concern determining which of the most popular technical analysis indicators have the greatest predictive power for a successful transaction with the feature importance method.

Machine-learning methods have recently been successfully used in different areas, but there are also many fields where such studies have not been carried out. One of them is advanced issue regarding liquidity prediction and forecasting of financial time series. It is a very challenging task because this sphere is highly volatile and dynamic, especially if we consider emerging stock markets like the Vietnamese one. The authors proposed deep learning as the most modern technique to forecast the future directions of an emerging stock market and developed a predictive model to forecast liquidity for such a market. A fully-connected neural network based on Multilayer Perceptron (MLP), Mixed Deep Learning (MDL), and Linear Regression (LR) was tested. The following metrics were used: mean absolute error (MAE) and mean square error (MSE), and the best values of MSE in the MDL model were achieved. Based on the proposed model, which is the main contribution of the paper, better investment decisions can be achieved. The authors’ solution is dedicated to and empirically verified on the Vietnamese stock market, so future works should extend the model to other ones, emerging and developed alike.

The article presents the problem related to evaluation of Forex trading strategies in multi-agent systems.The ratios based on financial measures cannot be assumed to be only evaluation criteria because other aspects determining effectiveness of the strategies, such as, for instance, investment risk, statistics on winning, and lost transactions, transaction costs, should also be taken into consideration.The aim of this paper is to review the general financial investments performance measures in relation to the performance analysis of trading strategies.The characteristics of the commonly used performance measures are outlined.The discussion will be illustrated by solutions developed in the trading support system, called A-Trader system.The performance analysis in A-Trader is detailed on real FOREX quotations.

The paper presents aspects related to developing methods for financial time series forecasting using deep learning in relation to multi-agent stock trading system, called A-Trader.On the basis of this model, an investment strategies in A-Trader system can be build.The first part of the paper briefly discusses a problem of financial time series on FOREX market.Classical neural networks and deep learning models are outlined, their performances are analyzed.The final part presents deployment and evaluation of a deep learning model implemented using H20 library as an agent of A-Trader system.

Providing financial e-services in the all areas involves taking decisions processes.Existing systems, also multi-agent systems, usually include only one of the earlier mentioned areas, and they are closed systems, available only to a small group of users.In addition, agents' knowledge in these systems is characterized by a certain degree of heterogeneity.Since in the decisive process one final decision is required, knowledge shall be automatically integrated.The aim of this paper is presentation of the author's method for knowledge integration in multi-agent decision support system of financial e-services.The first part of paper presents an architecture of the developed system, functioning of selected agents and a structure of agents' knowledge representation.Next, the developed method for integration of knowledge has been described.The last part of paper presents the results of research experiment to evaluate the effectiveness of the system and the developed method.I

The paper presents issues related to developing methods for fundamental analysis used to expand capabilities of multi-agent trading system, to better predict the financial market.The fundamental analysis indicators can be used as confirmation of decisions generated by other strategies of the system.The first part of the article discusses briefly the fundamental analysis issues in relation to the online trading on FOREX market.The statistical analysis of correlations of the different time series indicators and algorithms of fundamental analysis agents are examined.The final part discusses the results of the performance evaluation of selected investment strategies, including fundamental-based agents.

This paper presents issues related to a process of the automatic summarization of the text documents connected with economic knowledge performed by the cognitive agents in an integrated management information system.In contemporary companies, the unstructured knowledge is essential, mainly due to the possibility of obtaining better flexibility and competitiveness of the organization.Therefore more often the decision are taken in the enterprises on the basis of the summaries.The first part of the paper shortly presents the state-of-the-art in the considered field; next, the summarization process in the Cognitive Integrated Management Information System is characterized; the case study related with the summaries generating agent is presented in the last part of this paper.

The article presents the application of a fuzzy logic in building the trading agents of the a-Trader system. The system supports investment decisions on the FOREX market. The first part of the article contains a discussion related to the use of fuzzy logic as an agents' knowledge representation. Next, the algorithms of the selected fuzzy logic buy-sell decision agents are presented. In the last part of the article the agent performance is evaluated on real FOREX data.

This article presents the problem of knowledge conflicts identification in the architecture of cognitive agents.The agents operate at the decision support systems.The types and the sample of cognitive agents architecture was characterized in the first part of article.Next, the causes of knowledge conflicts was indicated.The final part of article contains the analysis of sources of knowledge conflicts and their examples related to decision-making process.

The article presents the performance analysis issues of buy-sell decisions agents' in a-Trader system.The system allows for supporting of investment decision on FOREX market.The first part of article contains a description of a a-Trader system.Next, the algorithms of the selected buy-sell decision agents is presented.In the last part of article the evaluation function of agents' performance is detailed, and the approach to performance analysis is proposed and illustrated.