Working Papers

Seria wydawnicza WNE WORKING PAPERS prowadzona jest przez WNE UW od 2008 r. i jak dotąd opublikowano w niej ponad 400 prac.

Seria WNE Working Papers służy szybkiemu upowszechnianiu wyników badań prowadzonych na Wydziale Nauk Ekonomicznych UW. Publikowane tu teksty mają charakter wersji roboczych (pre-printów): mogą być uzupełniane lub poprawiane w miarę postępu prac nad tekstem i procesu wydawniczego. Prezentujemy aktualną wersję udostępnioną przez autorów, opatrzoną datą oraz identyfikatorami DOI/ISSN – co ułatwia jej cytowanie i śledzenie kolejnych iteracji. Każdy dokument zachowuje pełne prawa autorskie swoich twórców, a w przypadku późniejszych zmian, autorzy mogą w dowolnym momencie zamieścić zaktualizowany plik lub wskazać miejsce ostatecznego wydania.

Do serii WORKING PAPERS przyjmowane są artykuły pracowników naukowych WNE UW oraz publikacje z konferencji organizowanych na WNE UW. Artykuły powinny dotyczyć ekonomii, mieć charakter oryginalnych prac badawczych, nie być wcześniej publikowane. Przyjmowane są wyłącznie teksty w języku angielskim.

Prace prosimy przesyłać e-mailem na adres: oDFCvPcJtTWhbH'k8~I?7L}RAUz]#[g05#`?K7VE9[V_zZx-?3D.bHJFg

Prosimy przesyłać dwa pliki:

(1) główny tekst bez podania tytułu artykułu oraz autorów (plik DOC/DOCX) oraz

(2) stronę tytułową zawierającą: tytuł opracowania, autorów oraz ich afiliację (plik DOC/DOCX). 

Przed przesłaniem tekstu prosimy zapoznać się z szczegółowymi wymogami edycyjnymi.

Redaktorem wydawniczym serii Working Papers jest dr Maciej Bukowski.

Ilość wyników 8

WP(19/2025)482. A survey of statistical arbitrage pairs trading strategies with non-machine learning methods, 2016-2023

Autorzy: Sun Yufei
This review examines the growing literature on pairs trading frameworks, which involve relative value arbitrage strategies between two or more securities. Existing research is categorized into five main categories: distance methods use nonparametric …

WP482. A survey of statistical arbitrage pairs trading strategies with non-machine learning methods, 2016-2023

This review examines the growing literature on pairs trading frameworks, which involve relative value arbitrage strategies between two or more securities. Existing research is categorized into five main categories: distance methods use nonparametric distance measures to identify pairs trading opportunities; cointegration methods rely on formal cointegration tests to reveal stationary time series of spreads; time series methods focus on finding optimal trading rules for mean-reverting spreads; stochastic control methods aim to determine the optimal portfolio holdings in pairs trading relative to other available securities; and the "Other Methods" category encompasses other relevant pairs trading frameworks, albeit with a more limited supporting literature. Through a comprehensive review of over 100 papers published between 2016 and 2023, the survey identifies the key strengths and weaknesses of each approach, providing insights relevant for future research and practical implementation.


DOI: https://doi.org/10.33138/2957-0506.2025.19.482
Sun Yufei
statistical arbitrage pairs trading distance method cointegration method time series method stochastic control method mean-reversion

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

Autorzy: 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(3/2024)439. Supervised Autoencoder MLP for Financial Time Series Forecasting

Autorzy: Bieganowski Bartosz, Ślepaczuk Robert
This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation…

WP439. Supervised Autoencoder MLP for Financial Time Series Forecasting

This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns, using the Sharpe and Information Ratios. The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2010, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance, highlighting the importance of precise parameter tuning. This paper also presents a derivation of a novel optimization metric that can be used with triple barrier labeling. The results of this study have substantial policy implications, suggesting that financial institutions and regulators could leverage techniques presented to enhance market stability and investor protection, while also encouraging more informed and strategic investment approaches in various financial sectors.


Bieganowski Bartosz, Ślepaczuk Robert
machine learning algorithmic investment strategy supervised autoencoders financial time series trading strategy risk-adjusted return

WP(27/2023)434. Predicting DJIA, NASDAQ and NYSE index prices using ARIMA and VAR models

Autorzy: Teymurzade Sahil, Ślepaczuk Robert
This paper implements automated trading strategies with buy/sell signals based on Autoregressive Integrated Moving Average (ARIMA) and Vector autoregression (VAR) models. ARIMA and VAR models are compared based on several forecast error measures and …

WP434. Predicting DJIA, NASDAQ and NYSE index prices using ARIMA and VAR models

This paper implements automated trading strategies with buy/sell signals based on Autoregressive Integrated Moving Average (ARIMA) and Vector autoregression (VAR) models. ARIMA and VAR models are compared based on several forecast error measures and investment performance statistics. The data used in this thesis are daily closing prices of Dow Jones Industrial Average, NASDAQ Composite and NYSE Composite indices. The trading period covers 20 years of data from 2000-11-30 to 2020-11-30. The sensitivity analysis is made by changing the initial parameters to test how robust the methods are to these changes. Results show that although ARIMA model performed remarkably well during the volatile periods, VAR based strategy had better investment performance and was less robust to the changes compared to the ARIMA based strategy. Additionally, we have found that error metrics might be insufficient to evaluate performance of forecasting models, as VAR with higher forecast errors outperformed ARIMA model in algorithmic trading strategies.


Teymurzade Sahil, Ślepaczuk Robert
ARIMA model VAR model time series analysis algorithmic trading strategies investment systems statistical models forecasting stock prices

WP(29/2022)405. The efficiency of various types of input layers of LSTM model in investment strategies on S&P500 index

Autorzy: Nguyen Thi Thu Giang, Ślepaczuk Robert
The study compares the use of various Long Short-Term Memory (LSTM) variants to conventional technical indicators for trading the S&P 500 index between 2011 and 2022. Two methods were used to test each strategy: a fixed training data set from 200…

WP405. The efficiency of various types of input layers of LSTM model in investment strategies on S&P500 index

The study compares the use of various Long Short-Term Memory (LSTM) variants to conventional technical indicators for trading the S&P 500 index between 2011 and 2022. Two methods were used to test each strategy: a fixed training data set from 2001–2010 and a rolling train–test window. Due to the input sensitivity of LSTM models, we concentrated on data processing and hyperparameter tuning to find the best model. Instead of using the traditional MSE function, we used the Mean Absolute Directional Loss (MADL) function based on recent research to enhance model performance. The models were assessed using the Information Ratio and the Modified Information Ratio, which considers the maximum drawdown and the sign of the annualized return compounded (ARC). LSTM models' performance was compared to benchmark strategies using the SMA, MACD, RSI, and Buy&Hold strategies. We rejected the hypothesis that algorithmic investment strategy using signals from LSTM model consisting only from daily returns in its input layer is more efficient. However, we could not reject the hypothesis that signals generated by LSTM model combining daily returns and technical indicators in its input layer are more efficient. The LSTM Extended model that combined daily returns with MACD and RSI in the input layer generated a better result than Buy&Hold and other strategies using a single technical indicator. The results of the sensitivity analysis show how sensitive this model is to inputs like sequence length, batch size, technical indicators, and the length of the rolling train - test window.


Nguyen Thi Thu Giang, Ślepaczuk Robert
algorithmic investment strategies machine learning testing architecture deep learning recurrent neural networks LSTM technical indicators forecasting financial-time series technical indicators hyperparameter tuning S&P 500 Index

WP(11/2021)359. Comparison of the accuracy in VaR forecasting for commodities using different methods of combining forecasts

Autorzy: Lis Szymon, Chlebus Marcin
No model dominates existing VaR forecasting comparisons. This problem may be solved by combine forecasts. This study investigates the daily volatility forecasting for commodities (gold, silver, oil, gas, copper) from 2000-2020 and identifies the sour…

WP359. Comparison of the accuracy in VaR forecasting for commodities using different methods of combining forecasts

No model dominates existing VaR forecasting comparisons. This problem may be solved by combine forecasts. This study investigates the daily volatility forecasting for commodities (gold, silver, oil, gas, copper) from 2000-2020 and identifies the source of performance improvements between individual GARCH models and combining forecasts methods (mean, the lowest, the highest, CQOM, quantile regression with the elastic net or LASSO regularization, random forests, gradient boosting, neural network) through the MCS. Results indicate that individual models achieve more accurate VaR forecasts for the confidence level of 0.975, but combined forecasts are more precise for 0.99. In most cases simple combining methods (mean or the lowest VaR) are the best. Such evidence demonstrates that combining forecasts is important to get better results from the existing models. The study shows that combining the forecasts allows for more accurate VaR forecasting, although it's difficult to find accurate, complex methods.


Lis Szymon, Chlebus Marcin
Combining forecasts Econometric models Finance Financial markets GARCH models Neural networks Regression Time series Risk Value-at-Risk Machine learning Model Confidence Set

WP(32/2020)338. Fractional differentiation and its use in machine learning

Autorzy: Gajda Janusz, Walasek Rafał
This article covers the implementation of fractional (non-integer order) differentiation on four datasets based on stock prices of main international stock indexes: WIG 20, S&P 500, DAX, Nikkei 225. This concept has been proposed by Lopez de Prad…

WP338. Fractional differentiation and its use in machine learning

This article covers the implementation of fractional (non-integer order) differentiation on four datasets based on stock prices of main international stock indexes: WIG 20, S&P 500, DAX, Nikkei 225. This concept has been proposed by Lopez de Prado to find the most appropriate balance between zero differentiation and fully differentiated time series. The aim is making time series stationary while keeping its memory and predictive power. This paper makes also the comparison between fractional and classical differentiation in terms of the effectiveness of artificial neural networks. This comparison is done in two viewpoints: Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The conclusion of the study is that fractionally differentiated time series performed better in trained ANN.


Gajda Janusz, Walasek Rafał
fractional differentiation financial time series stock exchange artificial neural networks

WP(27/2020)333. Predicting prices of S&P500 index using classical methods and recurrent neural networks

Autorzy: Kijewski Mateusz, Ślepaczuk Robert
This study implements algorithmic investment strategies with buy/sell signals based on classical methods and recurrent neural network model (LSTM). The research compares the performance of investment algorithms on time series of S&P500 index cove…

WP333. Predicting prices of S&P500 index using classical methods and recurrent neural networks

This study implements algorithmic investment strategies with buy/sell signals based on classical methods and recurrent neural network model (LSTM). The research compares the performance of investment algorithms on time series of S&P500 index covering 20 years of data from 2000 to 2020. This paper presents an approach for dynamic optimization of parameters during backtesting process by using rolling training-testing window. Every method was tested in terms of robustness to changes in parameters and evaluated by appropriate performance statistics e.g. Information Ratio, Maximum Drawdown, etc. Combination of signals from different methods was stable and outperformed benchmark of Buy & Hold strategy doubling its returns on the same level of risk. Detailed sensitivity analysis revealed that classical methods which used rolling training-testing window were significantly more robust to changes in parameters than LSTM model in which hyperparameters were selected heuristically.


Kijewski Mateusz, Ślepaczuk Robert
machine learning recurrent neural networks long short-term memory model time series analysis algorithmic investment strategies systematic transactional systems technical analysis ARIMA model
  • 1