Testing Mean-Reversion Portfolio Strategies on Recent Equity Data

Summary

This empirical study evaluates whether online portfolio strategies designed to exploit mean reversion perform well beyond benchmark datasets. It examines three approaches: passive aggressive mean reversion, online moving average reversion, and transaction cost optimization. The researchers use historical prices for S&P 500 constituents from 2000 through 2017, alongside established benchmark datasets, to investigate why these strategies can appear especially successful in commonly used tests and whether they also work on more recent market data.

The reported findings are cautionary: benchmark datasets may favor mean-reversion methods, and strong results on those datasets may not carry over to broader market conditions. The strategies can fail even when conditions seem favorable, particularly when explicit or implicit transaction costs are present. The document does not provide detailed performance figures, implementation choices, or cost assumptions, so it does not establish which method performs best or how results vary across individual periods. Its main lesson is to test portfolio strategies on representative data while accounting for trading frictions.

Key ideas

• The study evaluates PAMR, OLMAR, and transaction cost optimization strategies.
• It compares established benchmark datasets with historical S&P 500 constituent prices from 2000 to 2017.
• Benchmark datasets can favor mean-reversion strategies and may give an incomplete picture of performance.
• The tested strategies may fail even in apparently favorable conditions.
• Explicit and implicit transaction costs can undermine mean-reversion results.

Tags

# Empirical investigation of state-of-the-art mean reversion strategies for equity markets


# Empirical investigation of state-of-the-art mean reversion strategies for equity markets









Recent studies have shown that online portfolio selection strategies that exploit the mean reversion property can achieve excess return from equity markets. This paper empirically investigates the performance of state-of-the-art mean reversion strategies on real market data. The aims of the study are twofold. The first is to find out why the mean reversion strategies perform extremely well on well-known benchmark datasets, and the second is to test whether or not the mean reversion strategies work well on recent market data. The mean reversion strategies used in this study are the passive aggressive mean reversion (PAMR) strategy, the on-line moving average reversion (OLMAR) strategy, and the transaction cost optimization (TCO) strategies. To test the strategies, we use the historical prices of the stocks that constitute S\&P 500 index over the period from 2000 to 2017 as well as well-known benchmark datasets. Our findings are that the well-known benchmark datasets favor mean reversion strategies, and mean reversion strategies may fail even in favorable market conditions, especially when there exist explicit or implicit transaction costs.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.