Web-ADARE: A web-aided data repairing system

Abstract

Data repairing aims at discovering and correcting erroneous data in databases. In this paper, we develop Web-ADARE, an end-to-end web-aided data repairing system, to provide a feasible way to involve the vast data sources on the Web in data repairing. Our main attention in developing Web-ADARE is paid on the interaction problem between web-aided repairing and rule-based repairing, in order to minimize the Web consultation cost while reaching predefined quality requirements. The same interaction problem also exists in crowd-based methods but this is not yet formally defined and addressed. We first prove in theory that the optimal interaction scheme is not feasible to be achieved, and then propose an algorithm to identify a scheme for efficient interaction by investigating the inconsistencies and the dependencies between values in the repairing process. Extensive experiments on three data collections demonstrate the high repairing precision and recall of Web-ADARE, and the efficiency of the generated interaction scheme over several baseline ones.

Repair missing data to improve corporate credit risk prediction accuracy with multi-layer perceptron

“…The idea of data repair is to use existing data to mine data with predictive value or analytical value from existing samples by advanced technology (Chiang et al, 2016;Gu et al, 2017;Wei et al, 2019). Many studies used generative adversarial networks (GANs) and autoencoders to repair the optimal parameters for missing data (Campanile et al, 2020;Chang et al, 2020b;.…”