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: 6/[#'UV|\uI!0hR9BGW*eHE7P`d]#[.yNqlD=m=f#r~!J'~PM|n*$-YQQ 

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 18

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(14/2024)450. Construction and Hedging of Equity Index Options Portfolios

Authors: Wysocki Maciej, Ślepaczuk Robert
This research presents a comprehensive evaluation of systematic index option-writing strategies, focusing on S&P500 index options. We compare the performance of hedging strategies using the Black-Scholes-Merton (BSM) model and the Variance-Gamma …

WP450. Construction and Hedging of Equity Index Options Portfolios

This research presents a comprehensive evaluation of systematic index option-writing strategies, focusing on S&P500 index options. We compare the performance of hedging strategies using the Black-Scholes-Merton (BSM) model and the Variance-Gamma (VG) model, emphasizing varying moneyness levels and different sizing methods based on delta and the VIX Index. The study employs 1-minute data of S&P500 index options and index quotes spanning from 2018 to 2023. The analysis benchmarks hedged strategies against buy-and-hold and naked option-writing strategies, with a focus on risk-adjusted performance metrics including transaction costs. Portfolio delta approximations are derived using implied volatility for the BSM model and market-calibrated parameters for the VG model. Key findings reveal that system atic option-writing strategies can potentially yield superior returns compared to buy-and-hold benchmarks. The BSM model generally provided better hedging outcomes than the VG model, although the VG model showed profitability in certain naked strategies as a tool for position sizing. In terms of rehedging frequency, we found that intraday heding in 130-minute intervals provided both reliable protection against adverse market movements and a satisfactory returns profile.


DOI: https://doi.org/10.33138/2957-0506.2024.14.450
Wysocki Maciej, Ślepaczuk Robert
S&P500 Index options Option Pricing Models Black-Scholes-Merton model Variance-Gamma model Implied Volatility Volatility Risk Premium Volatility Spreads Dynamic Hedging

WP(27/2022)403. What makes Punks worthy? Valuation of Non-Fungible Tokens based on the CryptoPunks collection using the hedonic pricing method

Authors: Plachimowicz Ewelina, Wójcik Piotr
This article focuses on an attempt to value Non-Fungible Tokens from the CryptoPunks collection. Based on the data from January 2021 to July 2021, a hedonic pricing model was built, based on the transaction history and characteristics of a given NFT,…

WP403. What makes Punks worthy? Valuation of Non-Fungible Tokens based on the CryptoPunks collection using the hedonic pricing method

This article focuses on an attempt to value Non-Fungible Tokens from the CryptoPunks collection. Based on the data from January 2021 to July 2021, a hedonic pricing model was built, based on the transaction history and characteristics of a given NFT, as well as external markets variables - cryptocurrency prices (Bitcoin and Ethereum), natural gas prices and the popularity of the collection in social media (Twitter). According to the literature, we decided to build three regression models: Ordinary Least Squares model, XGBoost algorithm and bidirectional Long Short-Term Memory Model. Based on the results, we were able to prove that such complex issues as NFT valuation require more advanced methods than the classical regression model. In addition, we proved that one of the most important categories of variables in the case of NFT valuation is the history of token sales and its characteristics, indicating a particular rarity. Moreover, we have shown that the cryptocurrency and natural gas market is not an important factor in the NFT valuation. Finally, we proved that the increase in the popularity of tokens in social media translates into an increase in NFT prices, and this is an important element when trying to valuate tokens.


Plachimowicz Ewelina, Wójcik Piotr
NFT Non-Fungible Token pricing valuation luxury goods cryptocurrencies

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

WP(31/2020)337. Variance Gamma Model in Hedging Vanilla and Exotic Options

Authors: Bollin Bartłomiej, Ślepaczuk Robert
The aim of this research is to explore the performance of different option pricing models in hedging the exotic options using the FX data. We analyze the narrow class of Lévy processes - the Variance Gamma process in hedging vanilla, Asian and…

WP337. Variance Gamma Model in Hedging Vanilla and Exotic Options

The aim of this research is to explore the performance of different option pricing models in hedging the exotic options using the FX data. We analyze the narrow class of Lévy processes - the Variance Gamma process in hedging vanilla, Asian and lookback options. We pose a question of whether or not using additional level of complexity, by introducing more sophisticated models, improves the effectiveness of hedging options, assuming that hedging errors are measured as the differences between portfolio values according to the model and not real market data (which we don't have). We compare this model with its special case and the Black-Scholes model. We use the data for EURUSD currency pair assuming that option prices change according to the model (as we don't observe them directly). We use Monte Carlo methods in fitting the model's parameters. Our results are not in line with the previous literature as there are no signs of the Variance Gamma process being better than the Black-Scholes and it seems that all three models perform equally well.


Bollin Bartłomiej, Ślepaczuk Robert
Monte Carlo option pricing Variance Gamma BSM model Lévy processes FX market hedging Asian and lookback options

WP(19/2020)325. Artificial Neural Networks Performance in WIG20 Index Options Pricing

Authors: Wysocki Maciej, Ślepaczuk Robert
In this paper the performance of artificial neural networks in option pricing is analyzed and compared with the results obtained from the Black – Scholes – Merton model based on the historical volatility. The results are compared based on…

WP325. Artificial Neural Networks Performance in WIG20 Index Options Pricing

In this paper the performance of artificial neural networks in option pricing is analyzed and compared with the results obtained from the Black – Scholes – Merton model based on the historical volatility. The results are compared based on various error metrics calculated separately between three moneyness ratios. The market data-driven approach is taken in order to train and test the neural network on the real-world data from the Warsaw Stock Exchange. The artificial neural network does not provide more accurate option prices. The Black – Scholes – Merton model turned out to be more precise and robust to various market conditions. In addition, the bias of the forecasts obtained from the neural network differs significantly between moneyness states.


Wysocki Maciej, Ślepaczuk Robert
option pricing machine learning artificial neural networks implied volatility supervised learning index options Black – Scholes – Merton model

WP(10/2018)269. Corporate governance, tax evasion and business cycles

Authors: Kokoszczyński Ryszard, Mbara Gilbert
We develop an agency model of corporate tax evasion and auditing by a residual claimant government and embed it to a macroeconomic environment characterised by credit constraints. In our economy, tax auditing by the government reduces the information…

WP269. Corporate governance, tax evasion and business cycles

We develop an agency model of corporate tax evasion and auditing by a residual claimant government and embed it to a macroeconomic environment characterised by credit constraints. In our economy, tax auditing by the government reduces the information asymmetry between lenders and entrepreneurs with an investment opportunity. Corporate governance quality consequently affects macroeconomic variables; with changes in tax rates, auditing and quality of corporate governance having aggregate effects. We show that changes in the revenue system; tax and audit rates, can directly affect asset prices and inflate the effects of exogenous shocks to the economy.


DOI: http://doi.org.10.26405/WP/WNE/2018/269/010
Kokoszczyński Ryszard, Mbara Gilbert
corporate governance credit constraints taxation asset pricing tax evasion agency problem

WP(6/2018)265. Do cultural differences affect voluntary payment decisions? Evidence from guided tours

Authors: Kukla-Gryz Anna, Szewczyk Peter, Zagórska Katarzyna
We provide an empirical explanation for cross-country differences in the size of the voluntary payments made for a good offered in a Pay-What-You-Want payment scheme. Using a sample of almost 500 international travellers from 50 nations participating…

WP265. Do cultural differences affect voluntary payment decisions? Evidence from guided tours

We provide an empirical explanation for cross-country differences in the size of the voluntary payments made for a good offered in a Pay-What-You-Want payment scheme. Using a sample of almost 500 international travellers from 50 nations participating in a guided tour that uses a voluntary payment method, we analyse the relationship between the size of the average voluntary payments and national values defined by Hofstede’s Cultural Dimensions (1983) as well as selected values from the World Value Survey (WVS). Strong correlations between certain cultural values and average payment sizes are found.


DOI: http://doi.org.10.26405/WP/WNE/2018/265/006
Kukla-Gryz Anna, Szewczyk Peter, Zagórska Katarzyna
pay what you want cultural dimensions pricing strategies participative pricing

WP(10/2016)201. Applying Exogenous Variables and Regime Switching to Multifactor Models on Equity Indices

Authors: Sakowski Paweł, Ślepaczuk Robert, Wywiał Mateusz
This article aims to extend the evaluation of classic multifactor models of Carhart(1997) for the case of global equity indices and to expand analysis performed in Sakowski, Slepaczuk, and Wywial (2015). Our intention is to test several modifications…

WP201. Applying Exogenous Variables and Regime Switching to Multifactor Models on Equity Indices

This article aims to extend the evaluation of classic multifactor models of Carhart(1997) for the case of global equity indices and to expand analysis performed in Sakowski, Slepaczuk, and Wywial (2015). Our intention is to test several modifications of these models to take into account different dynamics of equity excess returns between emerging and developed equity indices. Proposed extensions include volatility regime switching mechanism (using dummy variables and the Markov approach) and three new risk factors based on realized volatility of index returns, percentage deviation from nominal GDP trend and capitalisation relative to GDP factor. Additional modifications include introduction of common and country specific variables in order to control for global risk where fluctuations of volatility of various assets, prices of commodities, currencies and rates is really important. Moreover, instead of using data for individual stocks (which is a common approach in the literature), we evaluate the performance of these models for weekly data of 81 world investable equity indices in the period of 2000-2015. Such approach is proposed to estimate equity risk premium for a single country. Empirical evidence from the first part reveals important differences between results for classical models estimated on single stocks (either in international or US-only frame work) and models evaluated for equity indices. Additionally, we observe substantial discrepancies between results for developed countries and emerging markets. The last part of this research helps us to understand results revealed in the first part. Thanks to introduction of new risk factors, and additional common and country specific variables we were able to increase explanatory power of our factor models especially in case of emerging market indices. Finally, using weekly data for the last 15 years we illustrate importance of model risk and data overfitting effects when drawing conclusions upon results of multifactor models.


Sakowski Paweł, Ślepaczuk Robert, Wywiał Mateusz
multi-factor models asset pricing models equity risk premia equity indices new risk factors sensitivity analysis book to market momentum market price of risk emerging and developed equity indices

WP(9/2016)200. Can We Invest Based on Equity Risk Premia and Risk Factors from Multi-Factor Models?

Authors: Sakowski Paweł, Ślepaczuk Robert, Wywiał Mateusz
We find that detailed analysis of multi-factor models makes it possible to propose investment strategies based on equity risk premium disequlibrium. We examine two investment algorithms built on weekly data of world equity indices for emerging and de…

WP200. Can We Invest Based on Equity Risk Premia and Risk Factors from Multi-Factor Models?

We find that detailed analysis of multi-factor models makes it possible to propose investment strategies based on equity risk premium disequlibrium. We examine two investment algorithms built on weekly data of world equity indices for emerging and developed countries in the period of 2000-2015. We create seven risk factors using additional data about market capitalisation, book value, country GDP and betas of equity indices. The first strategy utilises theoretical value of equity risk premium from seven-factor Markov-switching model with variables common for all countries and variables specific to developed/emerging countries. We compare theoretical with realised equity risk premium for a given index to undertake the buy/sell decisions. The second algorithm works only on eight risk factors and applies them as input variables to Markowitz models with alternative optimisation criteria (target risk, target return, maximum Sharpe ratio, minimum variance and equally weighted assets). Finally, we notice that the impact of risk factors on final results of investment strategy is much more important than the selection of a particular econometric model in order to correctly evaluate equity risk premium.


Sakowski Paweł, Ślepaczuk Robert, Wywiał Mateusz
investment algorithms multi-factor models Markov switching model asset pricing models equity risk premia risk factors Markowitz model
  • 1
  • 2