Multi-Task Learning for Stock Selection

@inproceedings{Ghosn1996MultiTaskLF,
  title={Multi-Task Learning for Stock Selection},
  author={Joumana Ghosn and Yoshua Bengio},
  booktitle={NIPS},
  year={1996}
}
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… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 31 extracted citations

55 Citations

02468'97'02'08'14
Citations per Year
Semantic Scholar estimates that this publication has 55 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 10 references

How to make a low-dimensional representation suitable for diverse tasks

  • N. Intrator, S. Edelman
  • Connection Science, Special issue on Transfer in…
  • 1996
1 Excerpt

Predicting the U.S. index of industrial production

  • J. Moody, U. Levin, S. Rehfuss
  • Neural Network World,
  • 1993

Similar Papers

Loading similar papers…