Predicting Stock Returns from Company Financials and Machine Learning

DOI

10.2991/978-94-6463-388-7_22How to use a DOI?

Keywords

stock market prediction; machine learning; financial ratios

Abstract

The accurate prediction of the performance of stocks in the stock market has been a longstanding problem in the field of finance and applied mathematics. We use financial statements data from the U.S. SEC and share price data from Kaggle to predict U.S. stock market returns using LightGBM. After training, we construct a daily portfolio from the predictions, which we backtested over the years 2015–2021, yielding annualized returns of 5.57% for the standard strategy, and 9.43% for the modified strategy, and Sharpe ratios of 0.855 and 0.956 respectively. Finally, we analyzed the relative importance of the features used, showing that momentum features are the most significant predictors, followed by days_since_ddate and Net Income-based features.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Aerjay Castañeda
AU  - Ligaya Leah Figueroa
PY  - 2024
DA  - 2024/02/29
TI  - Predicting Stock Returns from Company Financials and Machine Learning
BT  - Proceedings of the Workshop on Computation: Theory and Practice (WCTP 2023)
PB  - Atlantis Press
SP  - 369
EP  - 379
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-388-7_22
DO  - 10.2991/978-94-6463-388-7_22
ID  - Castañeda2024
ER  -