Relational data imputation with quality guarantee

Fengfeng Fan, Zhanhuai Li, Qun Chen, Lei Chen

Abstract: Highlights•We propose a novel probabilistic framework for relational data imputation based on the concept of generalized feature dependency.•We propose an imputation model with precision guarantee. We present the techniques to maximize recall while ensuring a user-specified precision level.•We demonstrate by extensive experiments on real data that the proposed framework performs better than the state-of-the-art alternatives and most importantly, its quality control mechanism is effective.