US 11,972,309 B2
Application programming interface anomaly detection
Nagraj K. Naidu, Foster City, CA (US); Sheeban Raza Zaheer Shaikh, Foster City, CA (US); Christopher Patrick, Foster City, CA (US); and Santanu Bhattacharya, Foster City, CA (US)
Assigned to Visa International Service Association, San Francisco, CA (US)
Filed by VISA INTERNATIONAL SERVICE ASSOCIATION, San Francisco, CA (US)
Filed on Jul. 25, 2022, as Appl. No. 17/872,277.
Application 17/872,277 is a continuation of application No. 16/589,990, filed on Oct. 1, 2019, granted, now 11,436,068.
Prior Publication US 2022/0374297 A1, Nov. 24, 2022
Int. Cl. G06F 9/54 (2006.01); G06Q 20/10 (2012.01); G06Q 20/20 (2012.01)
CPC G06F 9/547 (2013.01) [G06Q 20/10 (2013.01); G06Q 20/20 (2013.01); G06Q 20/202 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, at a central server, one or more application programming interface (API) requests requesting services provided by the central server;
identifying, by the central server, one or more of the received API requests associated with a merchant, the one or more of the received API requests comprise transactions with the merchant;
executing, by the central server, a rule to identify a set of the one or more of the received API requests belonging to a maximum percentile in a distribution configured by the central server and a set of the one or more of the received API requests belonging to a minimum percentile in the distribution;
in response to executing, estimating, by the central server, a set of anomalous data points associated with the one or more of the API requests while the one or more of the API requests continuing to be processed, wherein the anomalous data points being based on one or more goodness of fit functions against the maximum percentile and the minimum percentile;
providing, by the central server, a graphical user interface (GUI) to receive a critical value from a user, said critical value defining a tolerance level of anomalies associated with the API requests;
providing, by the central server, the GUI to receive from the user a selectable notification schedule and a selectable distribution model;
in response to the critical value, the selectable notification schedule, and the selectable distribution model, generating, by the central server, a recommendation of a distribution model as a function of the set of the anomalous data points, wherein the recommendation differs from the selectable distribution model; and
displaying, by the central server, a set of the anomalous data points as a function of the recommendation.