An R2R approach for stock prediction and portfolio optimization

Accurately predicting investment returns is one of the most widely investigated and challenging problems for investors and researchers. In this paper, we propose a Return-to-Return (R2R) mathematical approach for capturing return movements by simplifying feature-driven barriers and focusing only on daily return rate. In the R2R framework, we devise a security alignment technique and derive the Expected Alignment Deviation (EAD)-based predicting functions by considering the synchronous evolution of daily return deviations. The EAD matrix for all security in the portfolio serves as the foundation for the grouping method used to identify Key Security Leaders (KSLs) and predict security returns. Subsequently, we propose mean–variance portfolio optimization models that incorporate KSLs from each group. These models are transformed into two forms: continuous period and discrete period. Finally, we validate the effectiveness of our method through an experimental analysis of Chinese stocks.