Industry return prediction via interpretable deep learning

Lazaros Zografopoulos*, Maria Chiara Iannino, Ioannis Psaradellis, Georgios Sermpinis

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

We apply an interpretable machine learning model, the LassoNet, to forecast and trade U.S. industry portfolio returns. The model combines a regularization mechanism with a neural network architecture. A cooperative game-theoretic algorithm is also applied to interpret our findings. The latter hierarchizes the covariates based on their contribution to the overall model performance. Our findings reveal that the LassoNet outperforms various linear and nonlinear benchmarks concerning out-of-sample forecasting accuracy and provides economically meaningful and profitable predictions. Valuation ratios are the most crucial covariates, followed by individual and cross-industry lagged returns. The constructed industry ETF portfolios attain positive Sharpe ratios and positive and statistically significant alphas, surviving even transaction costs.
Original languageEnglish
Pages (from-to)257-268
Number of pages12
JournalEuropean Journal of Operational Research
Volume321
Issue number1
Early online date31 Aug 2024
DOIs
Publication statusE-pub ahead of print - 31 Aug 2024

Keywords / Materials (for Non-textual outputs)

  • finance
  • forecasting
  • Machine Leraning
  • deep learning
  • feature importance

Fingerprint

Dive into the research topics of 'Industry return prediction via interpretable deep learning'. Together they form a unique fingerprint.

Cite this