Deep Learning Replication for Statistical Arbitrage in Polish Equities
Summary
The study adapts a pairs trading framework to Polish equities by comparing an asset with a replication built from risk factors, rather than pairing it with a second highly correlated asset. It constructs factors using Principal Components Analysis, exchange traded funds, or Long Short Term Memory networks, then models the resulting residuals with an Ornstein-Uhlenbeck process. Signals are generated for portfolios whose residuals revert sufficiently quickly. The implementation uses Polish index constituents and local market assumptions, including risk-free rates and transaction costs.
The reported evaluation covers 2017–2019 and the recession year 2020. All approaches are profitable in the earlier period, with PCA reaching roughly 20 percent cumulative return and a Sharpe ratio up to 2.63. In 2020, the ETF approach remains profitable at about 5 percent annual return, while PCA and LSTM underperform. The evidence is limited to the stated periods and market adaptation; the negative LSTM results indicate that its performance is not established by this study.
Key ideas
- The strategy replicates an asset using risk factors instead of pairing it with a second correlated asset.
- PCA, ETFs, and LSTMs are used to construct the replication.
- Residuals are modeled with an Ornstein-Uhlenbeck process to identify mean-reverting signals.
- The study adapts the framework to Polish indices and local trading assumptions.
- PCA leads in the earlier test period, while only the ETF approach remains profitable during 2020.
Tags
Full text
# Statistical Arbitrage in Polish Equities Market Using Deep Learning Techniques # Statistical Arbitrage in Polish Equities Market Using Deep Learning Techniques We study a systematic approach to a popular Statistical Arbitrage technique: Pairs Trading. Instead of relying on two highly correlated assets, we replace the second asset with a replication of the first using risk factor representations. These factors are obtained through Principal Components Analysis (PCA), exchange traded funds (ETFs), and, as our main contribution, Long Short Term Memory networks (LSTMs). Residuals between the main asset and its replication are examined for mean reversion properties, and trading signals are generated for sufficiently fast mean reverting portfolios. Beyond introducing a deep learning based replication method, we adapt the framework of Avellaneda and Lee (2008) to the Polish market. Accordingly, components of WIG20, mWIG40, and selected sector indices replace the original S&P500 universe, and market parameters such as the risk free rate and transaction costs are updated to reflect local conditions. We outline the full strategy pipeline: risk factor construction, residual modeling via the Ornstein Uhlenbeck process, and signal generation. Each replication technique is described together with its practical implementation. Strategy performance is evaluated over two periods: 2017-2019 and the recessive year 2020. All methods yield profits in 2017-2019, with PCA achieving roughly 20 percent cumulative return and an annualized Sharpe ratio of up to 2.63. Despite multiple adaptations, our conclusions remain consistent with those of the original paper. During the COVID-19 recession, only the ETF based approach remains profitable (about 5 percent annual return), while PCA and LSTM methods underperform. LSTM results, although negative, are promising and indicate potential for future optimization.
Shown in full with attribution under the source's licence. Licence: abstract CC0
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.