US 11,699,082 B2
Multi-dimensional record correlations
Lukasz G. Cmielowski, Cracow (PL); Wojciech Sobala, Cracow (PL); Maksymilian Erazmus, Zasów (PL); and Rafal Bigaj, Cracow (PL)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Nov. 21, 2019, as Appl. No. 16/691,269.
Prior Publication US 2021/0158178 A1, May 27, 2021
Int. Cl. G06F 16/00 (2019.01); G06N 5/04 (2023.01); G06F 16/28 (2019.01); G06N 20/00 (2019.01)
CPC G06N 5/04 (2013.01) [G06F 16/285 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
assigning a set of transaction records, defining one or more recommendations made by an artificial intelligence (AI) decision engine, to a set of batches based on a set of record characteristics for the set of transaction records;
determining a set of batch characteristics for a batch of the set of batches;
determining one or more correlations among the set of batch characteristics;
comparing the one or more correlations with threshold correlations of one or more threshold batches; and
determining, from the one or more correlations and the comparing, an impact of one or more recommendations of the AI decision engine.