US 11,940,983 B1
Anomaly back-testing
Mohammad Adnan, Kent, WA (US); Mohammed Talal Yassar Azam, Snoqualmie, WA (US); Aditya Bahuguna, Seattle, WA (US); Fnu Syed Furqhan Ulla, Redmond, WA (US); Devesh Ratho, Seattle, WA (US); Ankita Verma, San Francisco, CA (US); and Ankur Mehrotra, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,486.
Int. Cl. G06F 16/23 (2019.01); G06N 20/20 (2019.01)
CPC G06F 16/2365 (2019.01) [G06N 20/20 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one processor; and
memory that stores computer-executable instructions that, in response to execution by the at least one processor, cause the system to at least:
receive, from a client, a request for a service to provide ongoing detection of anomalies in real-time data, the request comprising a dataset of historical data and an indication to use the dataset of historical data to back-test the service prior to initiating the ongoing detection of anomalies;
execute one or more workflows to upload the dataset of historical data, train a plurality of machine learning models to perform anomaly detection, and detect one or more anomalies in the dataset of historical data using the plurality of machine learning models, wherein the training is based at least in part on a first portion of the dataset of historical data, and wherein the anomaly detection is based at least in part on a second portion of the dataset of historical data;
provide, to the client, a representation of the one or more anomalies detected in the dataset of historical data by the plurality of machine learning models; and
receive, from the client in response to accepting the representation, an indication to provide the ongoing detection of anomalies in the real-time data using the plurality of machine learning models.