Supervised Stratified Subsampling for Predictive Analytics

Abstract

Predictive analytics involves the use of statistical models to make predictions; however, the power of these techniques is hindered by ever-increasing quantities of data. The richness and sheer volume of big data can have a profound effect on computation time and/or numerical stability. In the current study, we develop a novel approach to subsampling with the aim of overcoming this issue when dealing with regression problems in a supervised learning framework. The proposed method integrates stratified sampling and is model-independent. We assess the theoretical underpinnings of the proposed subsampling scheme, and demonstrate its efficacy in yielding reliable predictions with desirable robustness when applied to different statistical models.