Multi-Task Learning for Stock Selection
Abstract
Artificial Neural Networks can be used to predict future returns of stocks in order to take financial decisions . Should one build a separate network for each stock or share the same network for all the stocks? In this paper we also explore other alternatives, in which some layers are shared and others are not shared. When the prediction of future returns for different stocks are viewed as different tasks, sharing some parameters across stocks is a form of multi-task learning. In a series of experiments with Canadian stocks, we obtain yearly returns that are more than 14% above various benchmarks.
Cite
Text
Ghosn and Bengio. "Multi-Task Learning for Stock Selection." Neural Information Processing Systems, 1996.Markdown
[Ghosn and Bengio. "Multi-Task Learning for Stock Selection." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/ghosn1996neurips-multitask/)BibTeX
@inproceedings{ghosn1996neurips-multitask,
title = {{Multi-Task Learning for Stock Selection}},
author = {Ghosn, Joumana and Bengio, Yoshua},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {946-952},
url = {https://mlanthology.org/neurips/1996/ghosn1996neurips-multitask/}
}