RACORN-K: Risk-Aversion Pattern Matching-based Portfolio Selection

TL;DR

RACORN-K enhances pattern matching-based portfolio selection by incorporating risk aversion, leading to more reliable profits and better risk-adjusted returns, especially in volatile markets.

Contribution

It introduces a risk-averse modification to the CORN-K algorithm, improving portfolio performance by penalizing risk during optimization.

Findings

Improves return, Sharp ratio, and maximum drawdown.

Performs well on volatile markets.

Demonstrates significant improvements across four datasets.

Abstract

Portfolio selection is the central task for assets management, but it turns out to be very challenging. Methods based on pattern matching, particularly the CORN-K algorithm, have achieved promising performance on several stock markets. A key shortage of the existing pattern matching methods, however, is that the risk is largely ignored when optimizing portfolios, which may lead to unreliable profits, particularly in volatile markets. We present a risk-aversion CORN-K algorithm, RACORN-K, that penalizes risk when searching for optimal portfolios. Experiments on four datasets (DJIA, MSCI, SP500(N), HSI) demonstrate that the new algorithm can deliver notable and reliable improvements in terms of return, Sharp ratio and maximum drawdown, especially on volatile markets.