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: Vw%{3tUk+#oEvDNC^8[|Q07*.bP]#[Ngtgwc9\hvU4j[F.DEQtZpvz7S9 

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 4

WP(23/2025)486. Does Pair Trading Still Work During Extreme Events? A Comprehensive Empirical Evidence from Chinese Stock Market

Authors: Sun Yufei
This study evaluates the performance of pairs trading strategies in the Chinese stock market across extreme market environments, including the Financial Crisis, Bull and Bear phases, and the COVID-19 period. Using a comprehensive stock dataset and in…

WP486. Does Pair Trading Still Work During Extreme Events? A Comprehensive Empirical Evidence from Chinese Stock Market

This study evaluates the performance of pairs trading strategies in the Chinese stock market across extreme market environments, including the Financial Crisis, Bull and Bear phases, and the COVID-19 period. Using a comprehensive stock dataset and incorporating transaction costs, we find that most portfolios deliver near-zero excess returns after costs. However, in volatile conditions—especially during the Financial Crisis—top-performing portfolios achieved monthly returns up to 156 basis points. The strategy underperforms in stable or bullish markets with fewer mean-reversion opportunities. COVID-19 introduced challenges that further reduced profitability. Results highlight the critical role of transaction costs and the importance of advanced pair selection methods, such as combining the Sum of Squared Deviations (SSD), Hurst exponent, and the Number of Zero Crossings (NZC), which consistently outperform traditional approaches. While generally unprofitable, pairs trading can succeed under specific market regimes, offering insights into risk management and strategy adaptation.


DOI: https://doi.org/10.33138/2957-0506.2025.23.486
Sun Yufei
Pairs Trading Statistical Arbitrage Sum of Squared Deviations Hurst Exponent Chinese Stock Market

WP(21/2025)484. Performance of Pairs Trading Strategies Based on Principal Component Analysis Methods

Authors: Sun Yufei
This thesis examines market-neutral, mean-reversion-based statistical arbitrage strategies in the Chinese equity market, using two factor decomposition methods: Principal Component Analysis (PCA) and sector-based Exchange-Traded Funds (ETFs). Residua…

WP484. Performance of Pairs Trading Strategies Based on Principal Component Analysis Methods

This thesis examines market-neutral, mean-reversion-based statistical arbitrage strategies in the Chinese equity market, using two factor decomposition methods: Principal Component Analysis (PCA) and sector-based Exchange-Traded Funds (ETFs). Residual returns are modeled as mean-reverting Ornstein–Uhlenbeck (OU) processes, generating contrarian signals. A 60-day rolling window ensures out-of-sample estimation. Realistic frictions are included via a 10-basis-point round-trip cost. Backtests from 2005 to 2024 compare four configurations: synthetic ETFs, fixed PCA, dynamic PCA, and trading-time volume adjustments. Both PCA- and ETF-based strategies deliver robust Sharpe ratios near 0.90–0.95. PCA portfolios perform better under high cross-sectional volatility, while ETF-based models remain stable during structural shifts. Incorporating trading volume enhances returns, especially for ETF models. Sensitivity analysis highlights the importance of threshold tuning and rolling-window lengths. These findings stress the critical role of factor construction and signal design in market-neutral strategies, suggesting further improvement via adaptive PCA and volume-weighted signals.


DOI: https://doi.org/10.33138/2957-0506.2025.21.484
Sun Yufei
Quantitative Trading Pair Trading Principal Component Analysis Chinese Stock Market

WP(14/2025)477. Can Artificial Intelligence Trade the Stock Market?

Authors: Jędrzej Maskiewicz, Sakowski Paweł
The paper explores the use of Deep Reinforcement Learning (DRL) in stock market trading, focusing on two algorithms: Double Deep Q-Network (DDQN) and Proximal Policy Optimization (PPO) and compares them with Buy and Hold benchmark. It evaluates these…

WP477. Can Artificial Intelligence Trade the Stock Market?

The paper explores the use of Deep Reinforcement Learning (DRL) in stock market trading, focusing on two algorithms: Double Deep Q-Network (DDQN) and Proximal Policy Optimization (PPO) and compares them with Buy and Hold benchmark. It evaluates these algorithms across three currency pairs, the S&P 500 index and Bitcoin, on the daily data in the period of 2019-2023. The results demonstrate DRL's effectiveness in trading and its ability to manage risk by strategically avoiding trades in unfavorable conditions, providing a substantial edge over classical approaches, based on supervised learning in terms of risk-adjusted returns.


DOI: https://doi.org/10.33138/2957-0506.2025.14.477
Jędrzej Maskiewicz, Sakowski Paweł
Reinforcement Learning Deep Learning stock market algorithmic trading Double Deep Q-Network Proximal Policy Optimization

WP(14/2022)390. Investor Sentiment in Asset Pricing Models: A Review

Authors: Lis Szymon
Despite the number of works on investor sentiment in asset pricing models the results did not allow to obtain a coherent knowledge about this sentiment. Most of the researchers used different measures and various models to study the impact of sentime…

WP390. Investor Sentiment in Asset Pricing Models: A Review

Despite the number of works on investor sentiment in asset pricing models the results did not allow to obtain a coherent knowledge about this sentiment. Most of the researchers used different measures and various models to study the impact of sentiment on stocks returns. However, the empirical relationship between investor sentiment and stock market behavior remains unclear. This study focuses on reviewing the methodologies and empirical findings of 71 papers published between 2000 and 2021 that apply different investor sentiment measures for modeling returns. The research confirmed two out of the three research hypotheses that the investor sentiment proxies and higher complexity of the model with the investor sentiment indicator improve the coefficient of determination. The second one was rejected, however, this may be due to too small a sample. For the hypothesis that models with more complex sentiment have better predictive power than those with simpler proxies, the number of studies was insufficient to refer strongly to the hypothesis.


Lis Szymon
Investor sentiment Asset pricing Multifactor models Behavioral finance Risk factors stock market behavior
  • 1