Publication Type

Journal Article

Version

publishedVersion

Publication Date

4-2018

Abstract

Machine learning and artificial intelligence techniques have been applied to construct online portfolio selection strategies recently. A popular and state-of-the-art family of strategies is to explore the reversion phenomenon through online learning algorithms and statistical prediction models. Despite gaining promising results on some benchmark datasets, these strategies often adopt a single model based on a selection criterion (e.g., breakdown point) for predicting future price. However, such model selection is often unstable and may cause unnecessarily high variability in the final estimation, leading to poor prediction performance in real datasets and thus non-optimal portfolios. To overcome the drawbacks, in this article, we propose to exploit the reversion phenomenon by using combination forecasting estimators and design a novel online portfolio selection strategy, named Combination Forecasting Reversion (CFR), which outputs optimal portfolios based on the improved reversion estimator. We further present two efficient CFR implementations based on online Newton step (ONS) and online gradient descent (OGD) algorithms, respectively, and theoretically analyze their regret bounds, which guarantee that the online CFR model performs as well as the best CFR model inhindsight. We evaluate the proposed algorithmson various real markets with extensive experiments. Empirical results show that CFR can effectively overcome the drawbacks of existing reversion strategies and achieve the state-of-the-art performance.

Keywords

Combination forecasting estimators, Combination forecasting reversion, Mean reversion, Online learning, Portfolio selection

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

ACM Transactions on Intelligent Systems and Technology

Volume

9

Issue

5

ISSN

2157-6904

Identifier

10.1145/3200692

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/3200692

Download

Share

COinS