Anomaly detection

A computer-implemented method comprising:

• receiving a predictive request for an updateable trained first predictive model, the predictive request including input data;
• inputting the input data into a trained second predictive model and generating predictive output data, the trained second predictive model trained to detect an anomaly in input data as compared to previously received training data;
• based on the predictive output data, detecting an anomaly in the input data as compared to the previously received input data;
• receiving training data for updating the updateable trained first predictive model;
• generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.

A non-transitory computer storage medium encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

• receiving training data for updating an updateable trained first predictive model;
• inputting the training data into a trained second predictive model and generating predictive output data;
• based on the predictive output data, detecting an anomaly in the training data as compared to previously received training data;
• and
• generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.

A non-transitory computer storage medium encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

• receiving a predictive request for an updateable trained first predictive model, the predictive request including input data;
• inputting the input data into a trained second predictive model and generating predictive output data, the trained second predictive model trained to detect an anomaly in input data as compared to previously received training data;
• based on the predictive output data, detecting an anomaly in the input data as compared to the previously received input data;
• receiving training data for updating the updateable trained first predictive model;
• generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.

A system comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• A computer-implemented system comprising:
• receiving training data for updating an updateable trained first predictive model;
• inputting the training data into a trained second predictive model and generating predictive output data;
• based on the predictive output data, detecting an anomaly in the training data as compared to previously received training data;
• and
• generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.

A system comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• receiving a predictive request for an updateable trained first predictive model, the predictive request including input data;
• inputting the input data into a trained second predictive model and generating predictive output data, the trained second predictive model trained to detect an anomaly in input data as compared to previously received training data;
• based on the predictive output data, detecting an anomaly in the input data as compared to the previously received input data;
• receiving training data for updating the updateable trained first predictive model;
• generating a retrained first predictive model based on the updateable trained first predictive model, a training function and training data that includes the received training data and previously received training data, wherein the received training data is weighted differently than the previously received training data based on the detected anomaly.