US 11,704,220 B2
Machine learning based data monitoring
Rafal Bigaj, Cracow (PL); Lukasz G. Cmielowski, Cracow (PL); Wojciech Sobala, Cracow (PL); and Maksymilian Erazmus, Cracow (PL)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Apr. 11, 2022, as Appl. No. 17/717,408.
Application 17/717,408 is a continuation of application No. 16/832,215, filed on Mar. 27, 2020, granted, now 11,301,351.
Prior Publication US 2022/0237098 A1, Jul. 28, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 17/15 (2006.01); G06N 20/00 (2019.01); G06F 18/21 (2023.01)
CPC G06F 11/3409 (2013.01) [G06F 17/15 (2013.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01)] 15 Claims
OG exemplary drawing
 
1. A method for controlling operation of a computer system, the computer system being configured to perform data transactions and to evaluate a property of the data transactions using a machine learning (ML), model, the method comprising:
determining a set of analysis bins, wherein an analysis bin represents a set of values of an attribute of records of the data transactions;
computing an overall performance metric of the computer system, the overall performance metric indicating a transaction execution performance by the computer system for each analysis bin of the set of analysis bins using records of the transactions having attribute values that are represented by the analysis bin;
responsive to each analysis bin of the set of analysis bins having at least a minimum number of records, computing the ML performance metric in each analysis bin of the set of analysis bins; and
configuring the computer system, based on a correlation over the set of analysis bins between the computed overall performance metric and a ML performance metric, for enabling a positive correlation between the overall and ML performance metrics of further performed data transactions.