Internal Regret in On-Line Portfolio Selection
Abstract
This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize the cumulative internal regret for all possible market behaviors. Some of the introduced strategies, apart from achieving a small internal regret, achieve an accumulated wealth almost as large as that of the best constantly rebalanced portfolio. It is argued that the low-internal-regret property is related to stability and experiments on real stock exchange data demonstrate that the new strategies achieve usually better returns compared to some known algorithms.
Cite
Text
Stoltz and Lugosi. "Internal Regret in On-Line Portfolio Selection." Annual Conference on Computational Learning Theory, 2003. doi:10.1007/978-3-540-45167-9_30Markdown
[Stoltz and Lugosi. "Internal Regret in On-Line Portfolio Selection." Annual Conference on Computational Learning Theory, 2003.](https://mlanthology.org/colt/2003/stoltz2003colt-internal/) doi:10.1007/978-3-540-45167-9_30BibTeX
@inproceedings{stoltz2003colt-internal,
title = {{Internal Regret in On-Line Portfolio Selection}},
author = {Stoltz, Gilles and Lugosi, Gábor},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2003},
pages = {403-417},
doi = {10.1007/978-3-540-45167-9_30},
url = {https://mlanthology.org/colt/2003/stoltz2003colt-internal/}
}