Working Papers

The WNE Working Papers series has been published by the Faculty of Economic Sciences at the University of Warsaw since 2008.

The WNE Working Papers series provides a fast, open channel for disseminating research conducted at the Faculty of Economic Sciences, University of Warsaw. The papers hosted here are working versions (pre-prints) and may evolve as authors refine their analyses, incorporate feedback, or progress through formal peer-review. What you read is the current version released by the authors, timestamped and assigned DOI/ISSN identifiers to ensure precise citation and version tracking. Copyright remains with the authors, who may, at any time, upload a revised file or add a note directing readers to a later, peer-reviewed publication.

The Working Papers series accepts articles by research employees of the Faculty and publications from conferences organised at the Faculty of Economic Sciences at the University of Warsaw. Articles should be original research papers which have not been previously published, on the subject of economics.

Please send your paper by e-mail: g~Z/*om|O=r@&b2dPz{BFGvCLuA]#[_nMun^Um-#X/wy*S2&q6O&[5Uf* 

Please send 2 files:

(1) the main text without the title of the article and the authors (DOC/DOCX file) and

(2) the title page including: the title of the paper, the authors and their affiliation (DOC/DOCX file).

Please read the detailed editing requirements before submitting your text. 

Number of Results 36

WP(32/2026)526. Same Constraints in Changing Times? A Machine-Learning Approach to Childbearing and Fertility Intentions in Poland during and after the COVID-19 Pandemic

Authors: Kurowska Anna, Grabowska Magdalena, Świtała Maciej, Osiewalska Beata
While studies highlight COVID-19's disruptive impact on fertility, whether pandemic-era childbearing predictors remain informative post-crisis is less clear. Using Polish Familydemic panel data from 2021–2024 (N = 1,925, aged 18–49), …

WP526. Same Constraints in Changing Times? A Machine-Learning Approach to Childbearing and Fertility Intentions in Poland during and after the COVID-19 Pandemic

While studies highlight COVID-19's disruptive impact on fertility, whether pandemic-era childbearing predictors remain informative post-crisis is less clear. Using Polish Familydemic panel data from 2021–2024 (N = 1,925, aged 18–49), we apply theory-guided machine learning to evaluate a broad set of individual, employment, partnership, and family characteristics. Because short-term fertility intentions prove most predictive of childbearing, we model both actual births and firm positive intentions using random forest. The pandemic-trained model retained strong post-pandemic predictive performance (AUC-ROC = 0.86), demonstrating that pandemic-era drivers remain informative. Childbearing and intentions shared 16 of their top 20 predictors, highlighting common relational, demographic, and work–family factors. Relationship satisfaction, work–life balance, and domestic work division were particularly prominent, whereas prolonged school and childcare closures lowered predicted probabilities for both outcomes among parents. Ultimately, post-pandemic fertility dynamics reflect persistent constraints embedded in everyday family and working lives.


DOI: https://doi.org/10.33138/2957-0506.2026.32.526
Kurowska Anna, Grabowska Magdalena, Świtała Maciej, Osiewalska Beata
childbearing fertility intentions COVID-19 pandemic machine learning relationship satisfaction childcare closures

WP(18/2026)512. Painting Price: A Machine Learning Approach to Art Valuation. Proof of Concept and Market Structure Diagnosis

Authors: Okhrimenko Kostiantyn
This paper investigates the feasibility of predicting art prices using machine learning methods applied to a dataset of 20,905 paintings and drawings scraped from the Artsper online marketplace. We test tree-based ensemble models (Decision Tree, Rand…

WP512. Painting Price: A Machine Learning Approach to Art Valuation. Proof of Concept and Market Structure Diagnosis

This paper investigates the feasibility of predicting art prices using machine learning methods applied to a dataset of 20,905 paintings and drawings scraped from the Artsper online marketplace. We test tree-based ensemble models (Decision Tree, Random Forest, XGboost) and deep learning architectures (MLP, CNN, Fusion) on both tabular metadata and hand-crafted image features. Results consistently show poor predictive performance across all model types and feature sets. We argue that this outcome is not a methodological failure but a substantive finding: it constitutes a diagnosis of the market structure of contemporary art. Drawing on hedonic pricing theory (Rosen 1974), the sociology of cultural fields (Bourdieu 1993), and the economics of valuation (Velthuis 2005; Beckert and Rössel 2013), we propose a three-layer model of art price determinants: physical attributes (observable and partially captured by models), visual-aesthetic features (observable but poorly quantifiable), and narrative-reputational capital (largely unobservable in cross-sectional platform data).


DOI: https://doi.org/10.33138/2957-0506.2026.18.512
Okhrimenko Kostiantyn
art market machine learning hedonic pricing art valuation cultural economics XGboost CNN

WP(7/2026)501. Causal Inference under Algorithmic Interference: Identification and Estimation without SUTVA in Platform Economies

Authors: Ryłow Jakub
The Stable Unit Treatment Value Assumption (SUTVA) fails systematically in platform economies where a deterministic algorithm mediates all interactions, making interference structural and mechanistically knowable. We introduce algorithmic interferenc…

WP501. Causal Inference under Algorithmic Interference: Identification and Estimation without SUTVA in Platform Economies

The Stable Unit Treatment Value Assumption (SUTVA) fails systematically in platform economies where a deterministic algorithm mediates all interactions, making interference structural and mechanistically knowable. We introduce algorithmic interference — a structural potential-outcomes model in which spillovers flow through the platform's known decision rule — and construct the Debiased Algorithmic Instrumental Variable (DAIV) estimator: a cross-fitted semiparametric procedure combining Double Machine Learning with the IV equation implied by the algorithmic mechanism. Under local algorithmic monotonicity (LAM), both the ATE and CATE are point identified; without LAM the sharp identified set is characterised. DAIV is sqrt(n)-consistent, asymptotically normal, and semiparametrically efficient, with a formal LAM test supplied. A synthetic ride-sharing example (n = 10,000) shows that standard DML overstates the treatment effect by 52% relative to DAIV; a Hausman-type specification test strongly rejects no algorithmic interference.


DOI: https://doi.org/10.33138/2957-0506.2026.7.501
Ryłow Jakub
algorithmic interference SUTVA potential outcomes causal identification double machine learning platform economies instrumental variables semiparametric efficiency partial identification

WP(30/2025)493. Is smooth Energiewende possible? Improving the performance of climate policies in Germany by optimizing the risk of electricity delivery

Authors: Bandurski Jakub, Hałatek Eliza, Łaziński Adam, Künstler Michał
The Energiewende is a deep-rooted notion in the German economy. The main goal is to achieve climate neutrality by transitioning to renewable energy sources. However, the feasibility of this transition is partially hindered by power grid congestion, w…

WP493. Is smooth Energiewende possible? Improving the performance of climate policies in Germany by optimizing the risk of electricity delivery

The Energiewende is a deep-rooted notion in the German economy. The main goal is to achieve climate neutrality by transitioning to renewable energy sources. However, the feasibility of this transition is partially hindered by power grid congestion, which undermines system efficiency and leads to both economic and environmental costs. We address this issue by making a prediction of the likelihood of congestion occurrence within the German TenneT DE electricity network in the years 2020-2023. We propose a twofold approach offering a combination of advanced econometric models and state-of-the-art machine learning methods. We offer separate solutions for up congestion when additional energy needs to be pushed to the network as well as down congestion when energy needs to be pulled away from the network. Analyzing the CatBoost with XAI, we identify factors that play a significant role in driving redispatch events within the German electricity network.


DOI: https://doi.org/10.33138/2957-0506.2025.30.493
Bandurski Jakub, Hałatek Eliza, Łaziński Adam, Künstler Michał
energiewende econometrics machine learning climate policy catboost

WP(22/2025)485. A survey of statistical arbitrage pair trading with machine learning, deep learning, and reinforcement learning methods

Authors: Sun Yufei
Pair trading remains a cornerstone strategy in quantitative finance, having consistently attracted scholarly attention from both economists and computer scientists. Over recent decades, research has expanded beyond traditional linear frameworks&mdash…

WP485. A survey of statistical arbitrage pair trading with machine learning, deep learning, and reinforcement learning methods

Pair trading remains a cornerstone strategy in quantitative finance, having consistently attracted scholarly attention from both economists and computer scientists. Over recent decades, research has expanded beyond traditional linear frameworks—such as regression- and cointegration-based models—to embrace advanced methodologies, including machine learning (ML), deep learning (DL), reinforcement learning (RL), and deep reinforcement learning (DRL). These techniques have demonstrated superior capacity to capture nonlinear dependencies and complex dynamics in financial data, thereby enhancing predictive performance and strategy design.
Building on these academic developments, practitioners are increasingly deploying DL models to forecast asset price movements and volatility in equity and foreign exchange markets, leveraging the advantages of artificial intelligence (AI) for trading. In parallel, DRL has gained prominence in algorithmic trading, where agents can autonomously learn optimal trading policies by interacting with market environments, enabling systems that move beyond price prediction to dynamic signal generation and portfolio allocation.
This paper provides a comprehensive survey of ML-, DL-, RL-, and DRL-based approaches to pair trading within quantitative finance. By systematically reviewing existing studies and highlighting their methodological contributions, it offers researchers a structured foundation for replication and further development. In addition, the paper outlines promising avenues for future research that extend the application of AI-driven methods in statistical arbitrage and market microstructure analysis.


DOI: https://doi.org/10.33138/2957-0506.2025.22.485
Sun Yufei
Pair Trading Machine Learning Deep Learning Reinforcement Learning Deep Reinforcement Learning Artificial Intelligence Quantitative Trading

WP(27/2024)463. Informer in Algorithmic Investment Strategies on High Frequency Bitcoin Data

Authors: Filip Stefaniuk, Ślepaczuk Robert
The article investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Me…

WP463. Informer in Algorithmic Investment Strategies on High Frequency Bitcoin Data

The article investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Mean Absolute Directional Loss (GMADL) and Quantile loss, are proposed and evaluated against the Buy and Hold benchmark and two benchmark strategies based on technical indicators. The evaluation is conducted using data of various frequencies: 5 minute, 15 minute, and 30 minute intervals, over the 6 different periods. Although the Informer-based model with Quantile loss did not outperform the benchmark, two other models achieved better results. The performance of the model using RMSE loss worsens when used with higher frequency data while the model that uses novel GMADL loss function is benefiting from higher frequency data and when trained on 5 minute interval it beat all the other strategies on most of the testing periods. The primary contribution of this study is the application and assessment of the RMSE, GMADL and Quantile loss functions with the Informer model to forecast future returns, subsequently using these forecasts to develop automated trading strategies. The research provides evidence that employing an Informer model trained with the GMADL loss function can result in superior trading outcomes compared to the buy-and-hold approach.


DOI: https://doi.org/10.33138/2957-0506.2024.27.463
Filip Stefaniuk, Ślepaczuk Robert
Machine Learning Financial Series Forecasting Automated Trading Strategy Informer Transformer Bitcoin High Frequency Trading Statistics GMADL

WP(13/2024)449. The Hybrid Forecast of S&P 500 Volatility ensembled from VIX, GARCH and LSTM models

Authors: Natalia Roszyk, Ślepaczuk Robert
Predicting the S&P 500 index's volatility is crucial for investors and financial analysts as it helps in assessing market risk and making informed investment decisions. Volatility represents the level of uncertainty or risk related to the siz…

WP449. The Hybrid Forecast of S&P 500 Volatility ensembled from VIX, GARCH and LSTM models

Predicting the S&P 500 index's volatility is crucial for investors and financial analysts as it helps in assessing market risk and making informed investment decisions. Volatility represents the level of uncertainty or risk related to the size of changes in a security's value, making it an essential indicator for financial planning. This study explores four methods to improve the accuracy of volatility forecasts for the S&P 500: the established GARCH model, known for capturing historical volatility patterns; an LSTM network that utilizes past volatility and log returns; a hybrid LSTM-GARCH model that combines the strengths of both approaches; and an advanced version of the hybrid model that also factors in the VIX index to gauge market sentiment. This analysis is based on a daily dataset that includes data for S&P 500 and VIX index, covering the period from January 3, 2000, to December 21, 2023. Through rigorous testing and comparison, we found that machine learning approaches, particularly the hybrid LSTM models, significantly outperform the traditional GARCH model. The inclusion of the VIX index in the hybrid model further enhances its forecasting ability by incorporating real-time market sentiment. The results of this study offer valuable insights for achieving more accurate volatility predictions, enabling better risk management and strategic investment decisions in the volatile environment of the S&P 500.


DOI: https://doi.org/10.33138/2957-0506.2024.13.449
Natalia Roszyk, Ślepaczuk Robert
volatility forecasting LSTM-GARCH S&P 500 index hybrid forecasting models VIX index machine learning financial time series analysis walk-forward process hyperparameters tuning deep learning recurrent neural networks

WP(12/2024)448. Improving Realized LGD approximation: A Novel Framework with XGBoost for handling missing cash-flow data

Authors: Zuzanna Kostecka, Ślepaczuk Robert
The scope for the accurate calculation of the Loss Given Default (LGD) parameter is comprehensive in terms of financial data. In this research, we aim to explore methods for improving the approximation of realized LGD in conditions of limited access …

WP448. Improving Realized LGD approximation: A Novel Framework with XGBoost for handling missing cash-flow data

The scope for the accurate calculation of the Loss Given Default (LGD) parameter is comprehensive in terms of financial data. In this research, we aim to explore methods for improving the approximation of realized LGD in conditions of limited access to the cash-flow data. We enhance the performance of the method which relies on the differences between exposure values (delta outstanding approach) by employing the machine learning (ML) techniques. The research utilizes the data from the mortgage portfolio of one of the European countries and assumes the close resemblance for similar economic contexts. It incorporates non-financial variables and macroeconomic data related to the housing market, improving the accuracy of loss severity approximation. The proposed methodology attempts to mitigate the country-specific (related to the local legal) or portfolio-specific factors in aim to show the general advantage of applying ML techniques, rather than case-specific relation. We developed an XGBoost model that does not rely on cash-flow data yet enhances the accuracy of realized LGD estimation compared to results obtained with the delta outstanding approach. A novel aspect of our work is the detailed exploration of the delta outstanding approach and the methodology for addressing conditions of limited access to cash-flow data through machine learning models.


DOI: https://doi.org/10.33138/2957-0506.2024.12.448
Zuzanna Kostecka, Ślepaczuk Robert
LGD Credit risk Outstanding Machine Learning Missing data Mortgage loan financial statements macroeconomic data

WP(10/2024)446. Predictive modeling of foreign exchange trading signals using machine learning techniques

Authors: Sugarbayar Enkhbayar, Ślepaczuk Robert
This study aimed to apply the algorithmic trading strategy on major foreign exchange pairs and compare the performances of machine learning-based strategies and traditional trend-following strategies with benchmark strategies. It differs from other s…

WP446. Predictive modeling of foreign exchange trading signals using machine learning techniques

This study aimed to apply the algorithmic trading strategy on major foreign exchange pairs and compare the performances of machine learning-based strategies and traditional trend-following strategies with benchmark strategies. It differs from other studies in that it considered a wide variety of cases including different foreign exchange pairs, return methods, data frequency, and individual and integrated trading strategies. Ridge regression, KNN, RF, XGBoost, GBDT, ANN, LSTM, and GRU models were used for the machine learning-based strategy, while the MA cross strategy was employed for the trend-following strategy. Backtests were performed on 6 major pairs in the period from January 1, 2000, to June 30, 2023, and daily, and intraday data were used. The Sharpe ratio was considered as a metric used to refer to economic significance, and the independent t-test was used to determine statistical significance. The general findings of the study suggested that the currency market has become more efficient. The rise in efficiency is probably caused by the fact that more algorithms are being used in this market, and information spreads much faster. Instead of finding one trading strategy that works well on all major foreign exchange pairs, our study showed it’s possible to find an effective algorithmic trading strategy that generates a more effective trading signal in each specific case.


DOI: https://doi.org/10.33138/2957-0506.2024.10.446
Sugarbayar Enkhbayar, Ślepaczuk Robert
machine learning algorithmic trading foreign exchange market rolling walk-forward optimization technical indicators

WP(9/2024)445. Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities market

Authors: Korniejczuk Adam, Ślepaczuk Robert
The study seeks to develop an effective strategy based on the novel framework of statistical arbitrage based on graph clustering algorithms. Amalgamation of quantitative and machine learning methods, including the Kelly criterion, and an ensemble of …

WP445. Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities market

The study seeks to develop an effective strategy based on the novel framework of statistical arbitrage based on graph clustering algorithms. Amalgamation of quantitative and machine learning methods, including the Kelly criterion, and an ensemble of machine learning classifiers have been used to improve risk-adjusted returns and increase the immunity to transaction costs over existing approaches.  The study seeks to provide an integrated approach to optimal signal detection and risk management. As a part of this approach, innovative ways of optimizing take profit and stop loss functions for daily frequency trading strategies have been proposed and tested. All of the tested approaches outperformed appropriate benchmarks. The best combinations of the techniques and parameters demonstrated significantly better performance metrics than the relevant benchmarks. The results have been obtained under the assumption of realistic transaction costs, but are sensitive to the changes of some key parameters


DOI: https://doi.org/10.33138/2957-0506.2024.9.445
Korniejczuk Adam, Ślepaczuk Robert
graph clustering algorithms statistical arbitrage algorithmic investment strategies pair trading strategy Kelly criterion machine learning risk adjusted returns