The joint project of Quantitative Finance Research Group and Data Science Lab open seminars has been started in 2019/2020 academic year and was thought of as the place for discussion of the newest research ideas coming from the latest scientific articles. We focus on research from the area of data science, quantitative finance, financial econometrics, machine learning, and risk management.
——————————————————————————-
The schedule of the forthcoming meetings is as follows:
——————————————————————————-
- 2025-14-04, Monday, 5.30pm-7.00pm, 55th research seminar, title: “ Factor Zoo (.zip)“
authors: Matthias X. Hanauer
abstract:The number of factors allegedly driving the cross-section of stock returns has grown steadily over time. We explore how much this ‘factor zoo’ can be compressed, focusing on explaining the available alpha rather than the covariance matrix of factor returns. Our findings indicate that about 15 factors are enough to span the entire factor zoo. This evidence suggests that many factors are redundant but also that merely using a handful of factors, as in common asset pricing models, is insufficient. While the selected factor styles remain persistent, the specific style representatives vary over time, underscoring the importance of continuous factor innovation.
additional info: poster
published/working paper: SSRN paper
presentation: will be added soon
the recording of the presentation: will be added soon - 2025-03-17, Monday, 5.30pm-7.00pm, 54th research seminar, title: “ In the Beginning Was the Word: LLM-VaR and LLM-ES“
authors: Daniel Traian Pele
abstract:This study introduces LLM-VaR and LLM-ES, novel approaches utilizing general-purpose large language models (LLMs) for zero-shot forecasting of Value at Risk (VaR) and Expected Shortfall (ES). Using the LLMTime framework, these methods process financial time series data encoded as numerical strings, providing a flexible, assumption-free alternative to traditional risk estimation models such as GARCH and EWMA. Our empirical analysis reveals that LLMs perform effectively within a short-term historical context, particularly in highly volatile markets like cryptocurrencies. However, as the historical context lengthens, the accuracy of LLM-based methods diminishes, with conventional models proving superior for capturing long-term dependencies. These findings highlight the potential of LLMs as adaptable tools for risk assessment over recent historical windows, while underscoring the continued importance of traditional models for robust, long-term financial risk management.
additional info: poster
published/working paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon - 2025-03-03, Monday, 6.30pm-8.00pm, 53rd research seminar, title: “ Leveraging Convexity: Enhancing Global Equity Expected Returns with Trend-Following and Tail Risk Hedging Overlays “
authors: Bruno Schwalbach
abstract:This thesis demonstrates that overlaying a combination of trend-following and tail risk hedging strategies onto a global equity portfolio significantly enhances both historical risk-adjusted and absolute returns. Tail risk hedging mitigates equity risk most effectively during sudden market crashes, while trend-following notably supports equity during slower bear markets. These strategies are complementary in that the combination is demonstrated to mitigate severe drawdowns which occur during crises that have manifested both rapidly and gradually. In addition, the application of a trend-following strategy has generated positive returns on average during equity bull markets while remaining uncorrelated under normal conditions. Employing a portable alpha framework, the beta and alpha components of the Combination Overlay portfolio are separated. The performance of a 100% global equity portfolio is compared with a portfolio that embodies the Combination Overlay portfolio, which maintains the same 100% allocation to global equity (representing beta) and overlays it with trend-following and tail risk hedging strategies (representing alpha). The resulting portfolio returns remain largely driven by global equity performance but exhibit a large, positive, and statistically significant alpha of 0.38% per month after controlling for traditional equity factors, global government bond, and commodity excess returns. This alpha stems from a combination of an uncorrelated risk premium earned from the trend-following overlay and a reduction in variance drag due to the superior tail risk characteristics of the Combination Overlay portfolio, which leads to an improved compounding return profile relative to global equity.
additional info: poster
published/working paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2025-02-03, Monday, 6.30pm-8.00pm, 52th research seminar, title: “ Rebalance Timing Luck: Unveiling the Hidden Hand in Portfolio Returns “
authors: Corey Hoffstein
abstract:How much of your portfolio’s performance hinges on pure chance? Rebalance timing luck—an often-overlooked driver of investment outcomes—can significantly alter the trajectory of your strategy, sometimes in ways that defy expectations. This presentation dives into the mechanics and implications of rebalance timing, uncovering how periodic portfolio adjustments interact with market randomness to create significant variability in returns. Drawing insights from leading academic research and real-world case studies (including strategic asset allocation, factor portfolios, and option-based strategies), we’ll explore strategies to mitigate timing luck and control this hidden force.
additional info: poster
published/working paper: SSRN paper
presentation: presentation
the recording of the presentation: recording - 2025-01-27, Monday, 6.30pm-8.00pm, 51th research seminar, title: ” Informer in Algorithmic Investment Strategies on High Frequency Bitcoin Data”
authors: Filip Stefaniuk, Robert Ślepaczuk
abstract:The paper investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Two strategies using Informer models with different loss functions, Quantile loss and Generalized Mean Absolute Directional Loss (GMADL), 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 manage to outperform the benchmark, the model that uses novel GMADL loss function turned out to be benefiting from higher frequency data and beat all the other strategies on most of the testing periods. The primary contribution of this study is the application and assessment of the Quantile and GMADL 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.
additional info: poster
published/working paper: SSRN paper
presentation: presentation
the recording of the presentation: recording - 2025-01-20, Monday, 5.30pm-7.00pm, 50th research seminar, title: “ Snapshots of Stories: Utilising Transformer Networks for Short Video Selection from Long-form Content “
authors: Jakub Wujec, Jakub Żmujdzin, Marcin Chlebus, Piotr Wójcik
abstract:We propose an automated method for detecting highlights in long-form videos by leveraging user engagement data from YouTube’s ”Most Replayed” feature. Focusing on sports and comedy videos, we adapt the Unified Multimodal Transformer (UMT) framework to evaluate the effectiveness of category-specific versus mixed-category models and different labeling strategies. Our experiments demonstrate that algorithms can accurately identify highlights based on user feedback. We find that labeling strategy and content type affect highlight detection effectiveness. Specifically, in our experiments, percentile-based labeling was more effective with user engagement data, when compared to z-score method. We observed that category-specific models performed better on comedy videos, while mixed-category models showed improved performance on sports videos, suggesting that the optimal modeling approach may vary depending on the content type.
additional info: poster
published/working paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon
- 2024-12-02, Monday, 6.30pm-8.00pm, 49th research seminar, title: “ Can Artificial Intelligence Trade The Stock Market? “
authors: Jędrzej Maskiewicz, Paweł Sakowski
additional info: poster
published/working paper: will be added soon
presentation: presentation
the recording of the presentation: recording - 2024-11-18, Monday, 6.30pm-8.00pm, 48th research seminar, title: “ Conditioning cooperation with property rights in tragedy of the commons setting “
authors: Jakub Bandurski, Piotr Wójcik
additional info: poster
published/working paper: …
presentation: …
the recording of the presentation: recording - 2024-11-04, Monday, 6.30pm-8.00pm, 47th research seminar, title: ” In Pursuit of Trend-Following Beta: The Promise and Pitfalls of Replication”
authors: Steven Braun, Corey Hoffstein, Juliusz Jabłecki
additional info: poster
published/working paper: SSRN paper
presentation: presentation
the recording of the presentation: recording - 2024-10-14, Monday, 6.30pm-8.00pm, 46th research seminar, title: “ Nighttime Lights as a Proxy for Economic Development on a Local Level – The Case of the US “
authors: Patrick Sliz, Piotr Wójcik
additional info: poster
published/working paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2024-10-07, Monday, 6.40pm-8.00pm, 45th research seminar, title: “ Statistical arbitrage in multi-pair trading strategy based on graph clustering algorithms in US equities market “
authors: Adam Korniejczuk, Robert Ślepaczuk
additional info: poster
published/working paper: SSRN paper
published/working paper: arXiv paper
presentation: presentation
the recording of the presentation: recording - 2024-04-08, Monday, 6.30pm-7.45pm, 44th research seminar, title: “ Uncovering the Asymmetric Information Content of High-Frequency Options “
authors: Mattia Bevilacqua
additional info: poster
published/working paper: paper
presentation: will be added soon
the recording of the presentation: recording - 2024-03-25, Monday, 4.45pm-6.15pm, 43rd research seminar, title: “ Analyzing Bitcoin Movements through Artificial Intelligence Evaluation of Facebook Sentiments “
authors: Daniel Traian Pele
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: - 2024-03-04, Monday, 6.30pm-7.45pm, 42nd research seminar, title: “ Supervised Autoencoder MLP for Financial Time Series Forecasting “
authors: Bartosz Bieganowski, Robert Ślepaczuk
additional info: poster
published paper: paper
presentation: presentation
the recording of the presentation: recording - 2024-02-05, Monday, 5.45pm-7.00pm, 41st research seminar, title: ” On track to a green future: new insights on the impact of train transport on Warsaw suburban real estate market ”
authors: Paweł Sieczak, Piotr Wójcik
additional info: poster
published paper: will be added soon
presentation: presentation
the recording of the presentation: recording - 2023-12-04, Monday, 6.30pm-8.00pm, 40th research seminar, title: “ Low-Volatility Equity Strategies and Interest Rates: A Bittersweet Perspective “
authors: Juliusz Jabłecki
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon - 2023-11-27, Monday, 5.45pm-7.15pm, 39th research seminar, title: “ Beyond Yelp – predicting restaurant closures based on Google Maps data “
authors: Tomasz Starakiewicz and Piotr Wójcik
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2023-11-13, Monday, 6.30pm-8.00pm, 38th research seminar, title: “ Explaining and Forecasting Abnormal Returns and Volume by Investor Sentiment Indicators “
authors: Szymon Lis, Paweł Sakowski, Robert Ślepaczuk
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon - 2023-10-23, Monday, 5.45pm-7.15pm, 37th research seminar, title: “ How much is my harm worth? Predicting the amount of compensation for harm awarded by the Polish courts “
authors: Maciej Świtała
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2023-10-09, Monday, 6.30pm-8.00pm, 36th research seminar, title: “ Comprehensive Comparison of Quantitative Finance Models for Hedging of Options Portfolio“
authors: Maciej Wysocki, Robert Ślepaczuk
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2023-06-12, Monday, 6.30pm-8.00pm, 35th research seminar,title: “The Credit Card Debt Puzzle and Noncognitive Ability“
author: Hwan-Sik Choi
additional info: poster
published paper: working paper
presentation: will be added soon
the recording of the presentation: will be added soon - 2023-05-29, Monday, 5.00pm-6.30pm, 34th research seminar,title: “How to win Econometric Games”
authors: Mateusz Buczyński, Michał Kunster, Michał Woźniak
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2023-04-24, Monday, 5.00pm-6.30pm, 33rd research seminar,title: “Proof-of-work versus proof-of-stake coins as possible hedges against green and dirty energy“
authors: Barbara Będowska-Sójka, Agata Kliber
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording - 2023-04-03, Monday, 6.30pm-8.00pm, 32nd research seminar,title: “The Systemic Risk Approach Based on Implied and Realized Volatility“
authors: Paweł Sakowski, Rafał Sieradzki, Robert Ślepaczuk
additional info: poster
working paper: working paper
presentation: will be added soon
the recording of the presentation: recording - 2023-03-06, Monday, 6.30pm-8.00pm, 31st research seminar,title: “On Randomization of Affine Diffusion Processes with Application to Pricing of Options on VIX and S&P 500“
authors: Lech A. Grzelak
additional info: poster
working paper: working paper
presentation: presentation
the recording of the presentation: recording - 2023-02-27, Monday, 5.00pm-6.30pm, 30th research seminar,title: “Deep learning–based automated measurements of the scrotal circumference of Norwegian Red bulls from 3D images“
authors: Joanna Bremer, Michał Maj
additional info: poster
published paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon - 2023-02-06, Monday, 6.30pm-8.00pm, 29th research seminar,title: “The Properties of Alpha Risk Parity Portfolios“
authors: Jérôme Gava, Julien Turc
additional info: poster
published paper: published paper
presentation: will be added soon
the recording of the presentation: will be added soon - 2023-01-23, Monday, 3.00pm-6.00pm, 28th research seminar,
additional info: poster
3.00pm
title: “Crypto volatility forecasting: ML vs GARCH“
authors: Prof. Dr. Wolfgang Härdle
the recording of the presentation: recording
4:15pm-4:30pm
coffee break
4:30pm
title: “Cross-exchange Crypto Risk: A High-frequency Dynamic Network Perspective“
authors: Yifu Wang
the recording of the presentation: recording
5:10pm
title: “Quantinar – The 2P2 Platform for Knowledge Sharing“
authors: Raul Bag
the recording of the presentation: recording
- 2023-01-16, Monday, 6.30pm-8.00pm, 27th research seminar,title: “Performance and Flow of SRI Mutual Funds and Investors Sophistication“
authors: Olga Klinkowska, Yuan Zhao
additional info: poster
working paper: working paper
presentation: will be added soon
the recording of the presentation: recording
- 2022-12-19, Monday, 5.00pm-6.30pm, 26th research seminar,title: “Absorption capacity of regions in terms of supporting entrepreneurship under the EU
Cohesion Policy. New evidence“
authors: Marcin Wajda, Piotr Wójcik
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation: will be added soon
- 2022-12-05, Monday, 6.30pm-8.00pm, 25th research seminar,title: “Daily and intraday application of various architectures of the LSTM model in algorithmic investment strategies on Bitcoin and the S&P 500 Index “
authors: Katarzyna Kryńska, Robert Ślepaczuk
additional info: poster
working paper: working paper
presentation: presentation
the recording of the presentation: recording
- 2022-11-21, Monday, 5.00pm-6.30pm, 24th research seminar,title: “Is attention all you need for intraday Forex trading?“
authors: Przemysław Grądzki, Piotr Wójcik
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: recording
- 2022-11-07, Monday, 6.30pm-8.00pm, 23rd research seminar,title: “A comparison of LSTM and GRU architectures with novel walk-forward approach to algorithmic investment strategy“
authors: Illia Baranochnikov, Robert Ślepaczuk
additional info: poster
working paper: working paper
presentation: presentation
the recording of the presentation: recording
- 2022-10-24, Monday, 5.00pm-6.30pm, 22nd research seminar,title: “What makes Punks worthy? Valuation of Non-Fungible Tokens based on the CryptoPunks collectio“
authors: Ewelina Plachimowicz, Piotr Wójcik
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation: recording
- 2022-10-10, Monday, 6.30pm-8.00pm,title: “Investment Portfolio Optimization Based on Modern Portfolio Theory and Deep Learning Models“
authors: Maciej Wysocki, Paweł Sakowski
additional info: poster
working paper: working paper
presentation: presentation
the recording of the presentation: recording
- 2022-06-20, Monday, 5.00pm-6.00pm,title: “Satellite imaginary for social data science“
authors: Xaquín S. Perez-Sindin, Piotr Wójcik
additional info: poster
- 2022-05-09, Monday, 5.00pm-6.00pm,title: “The modeling of earnings per share of Polish companies for post-financial crisis period using random walk and ARIMA models“
authors: Wojciech Kuryłek
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: will be added soon
- 2022-04-11, Monday, 5.00pm-6.00pm,title: “Application of Machine Learning in Algorithmic Investment Strategies on Global Stock
markets“
authors: Jan Grudniewicz, Robert Ślepaczuk
additional info: poster
working paper: working paper
presentation: presentation
the recording of the presentation: recording
- 2022-03-21, Monday, 5.00pm-6.00pm,title: “LSTM in Algorithmic Investment Strategies on BTC and S&P500 index“
authors: Jakub Michańków, Paweł Sakowski, Robert Ślepaczuk
additional info: poster
final publication: paper
presentation: presentation
the recording of the presentation: recording
- 2022-02-28, Monday, 5.00pm-6.00pm,title: “Textual Content and Academic Selectivness. A Case of Economic Journals“
authors: Paweł Baranowski, Szymon Wójcik
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: recording
- 2022-01-17, Monday, 3.00pm-4.30pm,title: “Forecasting of the Day-Ahead Energy Prices“
authors: Maciej Przybyła, Piotr Wójcik
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: recording
- 2021-12-13, Monday, 3.00pm-4.30pm,title: “Effective Local Volatility Model – with Application to Pricing American Basket Options“
authors: Juliusz Jabłecki
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: recording
- 2021-11-22, Monday, 4.45pm-6.30pm,
title: “Analysis of the Effectiveness of the Polish Judicial System Using Topic Modelling Tools“
authors: Maciej Świtała (PhD student at WNE UW)
additional info: poster
working paper: will be added soon
presentation: presentation
the recording of the presentation: recording
- 2021-10-18, Monday, 3.00pm-4.30pm,
title: “Robust Optimisation Procedure in Algorithmic Investment Strategies“
authors: Sergio Castellano Gomez and Robert Ślepaczuk
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/4916/3768/6325/WNE_WP375.pdf
presentation: presentation
the recording of the presentation: recording
- 2021-06-21, Monday, 5.00pm-6.30pm,
title: “Enhanced Index Replication Based on Smart Beta and the Analysis of Distribution Moments“
authors: Kamil Korzeń and Robert Ślepaczuk
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/6916/2748/4276/WNE_WP366.pdf
presentation: presentation
the recording of the presentation: recording
- 2021-05-17, Monday, 5.00pm-6.30pm,
title: “Identification of Scams in Initial Coin Offerings with Machine Learning“
authors: Bedil Karimov and Piotr Wójcik
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation is available here: will be added soon
- 2021-04-19, Monday, 5.00pm-6.30pm,
title: “XAI Tools as a Part of the Best Practices in Model Selection for Business Decision Modelling. Example of marketing campaign success forecasting“
authors: Marcin Chlebus
additional info: poster
working paper: will be added soon
presentation: will be added soon
the recording of the presentation is available here: will be added soon
- 2021-03-22, Monday, 5.00pm-6.30pm,
title: “The impact of the content of Federal Open Market Committee post-meeting statements on financial markets – text mining approach“
authors: Ewelina Osowska, Piotr Wójcik
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/7216/0210/4545/WNE_WP339.pdf
presentation: will be added soon
the recording of the presentation is available here: recording
- 2021-02-22, Monday, 5.00pm-6.30pm,
title: “Investment Opportunities on the Cryptocurrency Market within the Markowitz Framework“
authors: Paweł Sakowski, Anna Turovtseva
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/5016/1041/4810/WNE_WP347.pdf
application: application
presentation: presentation
the recording of the presentation is available here: recording
- 2021-01-18, Monday, 5.00pm-6.30pm,
title: “What Factors Determine Unequal Suburbanisation? New Evidence from Warsaw, Poland“
authors: Honorata Bogusz, Szymon Winnicki, Piotr Wójcik
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/1216/0224/3666/WNE_WP340.pdf
the recording of the presentation is available here: https://lnkd.in/g7cV7iX
- 2020-12-14, Monday, 5.00pm-6.30pm,
title: “Artificial Neural Networks Performance in WIG20 Index Options Pricing”
authors: Maciej Wysocki, Robert Ślepaczuk
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/2615/9372/4397/WNE_WP325.pdf
presentation: presentation
- 2020-11-16, Monday, 5.00pm-6.30pm,
title: “Size Does Matter. A Study of the Required Window Size for Optimal Quality Market Risk Models“
authors: Mateusz Buczyński, Marcin Chlebus
additional info: poster
working paper: https://www.wne.uw.edu.pl/files/9215/9039/7402/WNE_WP315.pdf
the recording of the presentation is available here: https://lnkd.in/eiMwF3C
- 2020-01-21, Monday, 4.45pm-5.45pm,
title: ” We Just Explained the Factors of Growth with Machine Learning!“
authors: Piotr Wójcik, Bartłomiej Wieczorek
additional info: poster
where: Faculty of Economic Sciences, University of Warsaw, Warsaw, ul. Długa 44/50
room: B002
working paper: https://www.wne.uw.edu.pl/files/5216/0322/9893/WNE_WP344.pdf
- 2019-12-17, Monday, 4.45pm-5.45pm,
title: “Recurrent Neural Networks vs. Classical Methods in Investment Strategies “
authors: Mateusz Kijewski, Robert Ślepaczuk
additional info: poster
where: Faculty of Economic Sciences, University of Warsaw, Warsaw, ul. Długa 44/50
room: B002
presentation: presentation
working paper: https://www.wne.uw.edu.pl/files/6215/9765/7140/WNE_WP333.pdf
- 2019-11-19, Monday, 4.45pm-5.45pm,
title: “Predicting well-being based on features visible from space – the case of Warsaw!”
authors: Piotr Wójcik, Krystian Andruszek
additional info: poster
where: Faculty of Economic Sciences, University of Warsaw, Warsaw, ul. Długa 44/50
room: B002
working paper: https://www.wne.uw.edu.pl/files/1416/0322/8088/WNE_WP343.pdf - 2019-10-15, Monday, 4.45pm-5.45pm,
title: “Diversification with cryptocurrencies? OMG, really?! “
authors: Paweł Sakowski, Przemysław Ryś
additional info: poster
where: Faculty of Economic Sciences, University of Warsaw, Warsaw, ul. Długa 44/50
room: B002