We propose a portfolio rebalance framework that integrates machine learning modelsinto the mean-risk portfolios in multi-period settings with risk-aversion adjustment. In each period,the risk-aversion coefficient is adjusted automatically according to market trend movements predictedby machine learning models. We employ Gini’s Mean Difference (GMD) to specify the risk of aportfolio and use a set of technical indicators generated from a market index (e.g., SP 500 index) tofeed the machine learning models to predict market movements. Using a rolling-horizon approach,we conduct a series of computational tests with real financial data to evaluate the performance ofthe machine learning integrated portfolio rebalance framework. The empirical results show thatthe XGBoost model provides the best prediction of market movement, while the proposed portfoliorebalance strategy generates portfolios with superior out-of-sample performances in terms of averagereturns, time-series cumulative returns, and annualized returns compared to the benchmarks.
展开▼
