This open-source tool, written in Python, referred to as XAI StatArb, implements a machine learning approach (ML) powered by eXplainable Artificial Intelligence techniques integrated into a statistical arbitrage trading pipeline. Specifically, given a set of stocks and their raw financial information, the tool aims at forecasting the next day’s return. Based on the predicted return, we trade the underperforming and overperforming stocks. Additionally, the tool contains three ML methods to discard irrelevant features for the prediction task. They are aimed at improving not only the prediction performance at the stock level but also overall at the stock set level.
CARTA Salvatore;
CONSOLI Sergio;
PODDA Alessandro Sebastian;
REFORGIATO RECUPERO Diego;
STANCIU Maria Madalina;
2022-08-05
Elsevier
JRC130129
2665-9638 (online),
https://www.sciencedirect.com/science/article/pii/S2665963822000690,
https://publications.jrc.ec.europa.eu/repository/handle/JRC130129,
10.1016/j.simpa.2022.100354 (online),
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|