Learning with Changing Features
This addresses the challenge of adapting machine learning models to evolving data in domains like retail and manufacturing, representing a novel contribution as the first formal study of change point detection in a distribution-independent agnostic setting.
The paper tackles the problem of detecting when features become relevant or change interpretation over time in supervised learning, proposing an approach that provably identifies such change points and demonstrating its application on retail and manufacturing data.
In this paper we study the setting where features are added or change interpretation over time, which has applications in multiple domains such as retail, manufacturing, finance. In particular, we propose an approach to provably determine the time instant from which the new/changed features start becoming relevant with respect to an output variable in an agnostic (supervised) learning setting. We also suggest an efficient version of our approach which has the same asymptotic performance. Moreover, our theory also applies when we have more than one such change point. Independent post analysis of a change point identified by our method for a large retailer revealed that it corresponded in time with certain unflattering news stories about a brand that resulted in the change in customer behavior. We also applied our method to data from an advanced manufacturing plant identifying the time instant from which downstream features became relevant. To the best of our knowledge this is the first work that formally studies change point detection in a distribution independent agnostic setting, where the change point is based on the changing relationship between input and output.