WOWitold Orzeszko

Witold Orzeszko

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Witold Orzeszko has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    News sentiment analysis using ChatGPT for Bitcoin price dynamics

    by Piotr Fiszeder, Witold Orzeszko, Radosław Pietrzyk

    This study investigates the use of ChatGPT as an automated tool for extracting and labeling Bitcoin-related news sentiment and examines how the resulting sentiment indicators affect Bitcoin returns and volatility. A large dataset of news headlines is processed via an API-based workflow, and the ChatGPT-derived sentiment indicators are subsequently incorporated as explanatory variables into selected statistical and machine learning models, including autoregressive (AR), heterogeneous autoregressive (HAR), Bayesian model averaging (BMA), least absolute shrinkage and selection operator (LASSO), and support vector regression (SVR). We find that while the sentiment indicators significantly improve in-sample estimation accuracy for returns and volatility, they do not lead to statistically significant gains in out-of-sample forecasting performance. This result suggests that ChatGPT-based sentiment measures primarily capture contemporaneous market-relevant information rather than persistent predictive signals, consistent with semi-strong market efficiency.


  • Artificial intelligence in project KPIs prediction: A systematic scoping review of machine learning approach

    by Jakub Polaszek, Witold Orzeszko

    The rapid growth of artificial intelligence and machine learning applications in project management is transforming the prediction of key performance indicators (KPIs). This has led to increased interest from both practitioners and the academic community, as reflected in the growing number of publications, creating a need for a comprehensive review. This paper presents a systematic scoping review of 688 peer-reviewed publications spanning three decades, analyzing the application of machine learning methods for predicting project KPIs across industries. The study aims to provide a comprehensive overview of current knowledge, offering insights and future research directions to advance the field and encourage greater innovation and efficiency in project management. The review focuses on identifying key patterns and trends in the data and exploring the potential of machine learning to enhance project outcomes. It also addresses the challenges and limitations of adopting these techniques. It reveals that machine learning applications are predominantly focused on cost and schedule performance prediction, with neural network-based approaches emerging as the most widely used techniques across industries. The findings indicate consistent improvements in predictive performance in complex project environments, while highlighting persistent challenges in data quality, model interpretability, and integration with existing project management systems.

  • Open Access

    Identifying Determinants of Exchange Rates: A Machine Learning Perspective

    by Michał Buszko, Witold Orzeszko

    Exchange rates are key economic variables that shape international competitiveness; yet, there is no consensus on the universal factors determining their dynamics under floating regimes. This study identifies the determinants of exchange rates for six major currencies using a machine learning framework. We apply LASSO and selected tree-based algorithms to infer relationships directly from empirical data. The results indicate that the set of relevant determinants is relatively narrow and varies across currencies. No systematic lagged effects are identified. Overall, exchange rates are found to be driven primarily by contemporaneous stock market developments, proxied by the DJIA, and selected commodity prices.

  • Open Access

    Identification of Bitcoin volatility drivers using statistical and machine learning methods

    by Piotr Fiszeder, Witold Orzeszko, Radosław Pietrzyk, Grzegorz Dudek


  • Open Access

    Machine learning in project schedule creation: a systematic literature review

    by Maciej Koszykowski, Witold Orzeszko

    Addressing the growing demand for autonomous project scheduling, this study explores the use of machine learning (ML) for project schedule creation. It is a well-known fact that ML surpasses human capabilities in analyzing extensive data. For this reason, ML is a promising domain for organizations that gather project experience. However, the current ML adoption in project management remains limited, lacking systematic studies demonstrating its potential. This is the first study that presents a comprehensive review of the current state of knowledge in the project schedule creation area. We summarize the ML techniques used in each schedule creation area and investigate their demonstrated potential in improving schedule creation processes. Moreover, we analyze in which industries such methods are most often used. Furthermore, we explore anticipated advancements, highlight potential benefits, and address current limitations of ML applications in the domain of schedule creation. We also uncover key gaps in research, discuss related challenges, and emerging trends. Additionally, we elaborate on practical implementation strategies for ML-based schedule creation, emphasizing that while ML has the potential to enhance project scheduling, full automation is unlikely in the near future. Instead, automating specific subprocesses appears to be the most practical approach for integrating ML into schedule creation at this stage.


  • Open Access

    Probabilistic Forecasting Cryptocurrencies Volatility: From Point to Quantile Forecasts

    by Grzegorz Dudek, Witold Orzeszko, Piotr Fiszeder

    Cryptocurrency markets are characterized by extreme volatility, making accurate forecasts essential for effective risk management and informed trading strategies. Traditional deterministic (point) forecasting methods are inadequate for capturing the full spectrum of potential volatility outcomes, underscoring the importance of probabilistic approaches. To address this limitation, this paper introduces probabilistic forecasting methods that leverage point forecasts from a wide range of base models, including statistical (HAR, GARCH, ARFIMA) and machine learning (e.g. LASSO, SVR, MLP, Random Forest, LSTM) algorithms, to estimate conditional quantiles of cryptocurrency realized variance. To the best of our knowledge, this is the first study in the literature to propose and systematically evaluate probabilistic forecasts of variance in cryptocurrency markets based on predictions derived from multiple base models. Our empirical results for Bitcoin demonstrate that the Quantile Estimation through Residual Simulation (QRS) method, particularly when applied to linear base models operating on log-transformed realized volatility data, consistently outperforms more sophisticated alternatives. Additionally, we highlight the robustness of the probabilistic stacking framework, providing comprehensive insights into uncertainty and risk inherent in cryptocurrency volatility forecasting. This research fills a significant gap in the literature, contributing practical probabilistic forecasting methodologies tailored specifically to cryptocurrency markets.

  • Open Access

    Real Estate Valuation Algorithm Using Nonparametric Regression Methods

    by Witold Orzeszko, Marcin Fałdziński, Ewa Siemińska

    Motivation: Real estate valuation is critical for various market participants and is influenced by numerous factors such as geographic location, property characteristics, and market trends. Traditional valuation methods often struggle to handle the complexity, scale, and dynamic nature of real estate markets. Automated valuation models (AVMs) have emerged as a promising alternative, offering scalability, speed, and adaptability. However, their effectiveness depends heavily on the ability to manage diverse data and model nonlinear relationships in valuation. Aim: This paper presents a novel algorithm for real estate valuation based on nonparametric regression methods, including local-linear kernel and Nadaraya-Watson estimators. The algorithm is designed to handle missing data, incorporate multiple influencing factors with adjustable weights, and adapt to dynamic market conditions. It aims to provide accurate property valuations by leveraging a systematic and flexible approach to segment data, select nearest neighbors, and update prices based on market trends. Results: The proposed algorithm demonstrates robustness to data errors, flexibility in handling variables measured on different scales, and the capacity to model nonlinear relationships. It effectively estimates property values using a comprehensive eight-stage process, from data preparation to quality assessment. The proposed algorithm is designed to be scalable and adaptable, making it a promising tool for addressing the challenges of real estate valuation across diverse contexts.

  • Open Access

    Prediction of robo-advisory acceptance in banking services using tree-based algorithms

    by Witold Orzeszko, Dariusz Piotrowski

    The banking sector is increasingly recognising the need to implement robo-advisory. The introduction of this service may lead to increased efficiency of banks, improved quality of customer service, and a strengthened image of banks as innovative institutions. Robo-advisory uses data relating to customers, their behaviors and preferences obtained by banks from various communication channels. In the research carried out in the work, an attempt was made to obtain an answer to the question whether the data collected by banks can also be used to determine the degree of consumer interest in this type of service. This is important because the identification of customers interested in the service will allow banks to direct a properly prepared message to a selected group of addressees, increasing the effectiveness of their promotional activities. The aim of the article is to construct and examine the effectiveness of predictive models of consumer acceptance of robo-advisory services provided by banks. Based on the authors’ survey on the use of artificial intelligence technology in the banking sector in Poland, in this article we construct tree-based models to predict customers’ attitudes towards using robo-advisory in banking services using, as predictors, their socio-demographic characteristics, behaviours and attitudes towards modern digital technologies, experience in using banking services, as well as trust towards banks. In our study, we use selected machine learning algorithms, including a decision tree and several tree-based ensemble models. We showed that constructed models allow to effectively predict consumer acceptance of robo-advisory services.


  • Open Access

    Artificial intelligence and customers’ intention to use robo-advisory in banking services

    by Dariusz Piotrowski, Witold Orzeszko

    Research background: Robo-advisory is a modern and rapidly developing area of implementing artificial intelligence to support customer decision-making. The current significance of robo-advisory to the financial sector is minor or marginal, and boils down to formulating recommendations and implementing investment strategies. However, the ongoing digital transformation of the economy leads us to believe that in the near future this technology will also be much more widely used with banking products. This makes it necessary for banks and other financial institutions to be prepared to offer this service to their customers. Purpose of the article: The aim of this paper is to identify factors significantly influencing bank customers’ intention to use robo-advisory. Identification of robo-advisory acceptance factors may increase the effectiveness of banks' promotional activities regarding such a service. Methods: Empirical data was obtained through a survey conducted on a representative sample of 911 Polish respondents aged 18–65. Using a multilevel ordered logit model and methods based on machine learning algorithms, the authors identified variables relating to the demographic and socio-economic characteristics, behaviors, and attitudes of consumers that primarily determine respondents’ adoption of robo-advisory. Findings & value added: The results of the study indicate that the variables regarding the respondents' attitude towards the use of artificial intelligence in banking services turned out to be the most important from the point of view of acceptance of robo-advisory. Next in terms of importance were the variables presenting respondents' assessments of the ethics of financial services. An important finding is that experience in using basic financial services is not a significant factor when accepting robo-advisory. From the practical perspective, the article provides recommendations on the use of artificial intelligence technology in finance and ethical aspects of the provision of such services by banks.


  • Prognozowanie szeregów czasowych w ekonomii i finansach z wykorzystaniem metod uczenia maszynowego. Wybrane modele i zastosowania

    by Witold Orzeszko, Grzegorz Dudek, Michał Dominik Stasiak, Marcin Stawarz

    Effective forecasting of economic and financial processes is of fundamental significance for participants and analysts of economic life. At the same time, however, many areas can be identified where forecasting tools that provide results with satisfactory accuracy are still missing. For this reason, continuous work has been underway concerning new methodological concepts and the improvement of existing forecasting tools. In recent years, the potential of machine learning algorithms has been noticed, as evidenced by their growing popularity both in the scientific community and among business practitioners. The monograph is devoted to the use of innovative machine learning methods for forecasting financial and economic time series. It presents selected prediction algorithms, emphasising the possibilities of their application. The results of the research presented in this monograph confirm the advantages of machine learning, in particular the fact that the described algorithms can be an effective tool for forecasting economic and financial time series.