US 12,468,960 B1
Prediction model training using detected anomalies
Kiran Prabhakara, Fremont, CA (US); Arun Krishnaswamy, San Ramon, CA (US); Venu Kasyap Tangirala, Mountain View, CA (US); Changsheng Chen, Orinda, CA (US); Roy Sturgeon, El Granada, CA (US); and Ganesh Rajaratnam, Fremont, CA (US)
Assigned to Workday, Inc., Pleasanton, CA (US)
Filed by Workday, Inc., Pleasanton, CA (US)
Filed on Oct. 14, 2019, as Appl. No. 16/601,309.
Int. Cl. G06N 20/00 (2019.01); G06N 5/01 (2023.01); G06N 5/022 (2023.01); G06N 5/04 (2023.01)
CPC G06N 5/04 (2013.01) [G06N 5/01 (2023.01); G06N 5/022 (2013.01); G06N 20/00 (2019.01)] 13 Claims
OG exemplary drawing
 
1. A system for a prediction model, comprising:
an interface configured to:
receive historical data; and
a processor configured to:
determine a training data set and a test data set from the historical data;
train a plurality of models using the training data set to obtain a plurality of trained models;
determine a best trained model of the plurality of trained models using the test data set;
select hyperparameters associated with the best trained model;
generate a prediction model using the hyperparameters and the historical data to obtain a trained prediction model;
receive a forecast;
determine an output of the trained prediction model corresponding to the forecast;
determine at least one detected anomaly based on a difference between the forecast and the output of the trained prediction model exceeding a threshold;
provide the forecast, the output of the trained model, and the at least one detected anomaly to a user using a user feedback interface;
receive user feedback from the user using the user feedback interface, wherein the user feedback comprises:
a false detected anomaly indication indicating that the at least one anomaly is not an anomaly; and
an undetected anomaly indication indicating that an undetected anomaly is an anomaly; and
retrain the trained prediction model using the hyperparameters and the user feedback to obtain a retrained prediction model.