Machine learning approach for solving the cold start problem in stateful models

A method for a computing system to use a user generated initial profile including known behavioral patterns to detect anomalies in received data using a first machine-learning model while in parallel training a second machine-learning model to learn the behavioral patterns of the received data so that the second machine-learning model can detect the anomalies, the method comprising:

• generating, from user input received from a user of a computing system, an initial profile that specifies expected behavioral patterns of datasets that are to be received by the computing system;
• extracting from one or more received datasets received by the computing system one or more features that are indicative of behavioral patterns of the one or more received datasets;
• providing the initial profile to one or more first machine-learning models, the one or more first machine-learning models having been trained using a subset of the one or more datasets, the one or more first machine-learning models using the initial profile to determine if the behavioral patterns of the received datasets are anomalous;
• and
• at one or more second machine-learning models that have been trained using a subset of the one or more datasets, training a second profile based on the one or more features to specify behavioral patterns of the received datasets that are learned by the second machine-learning model.

A computer program product comprising one or more computer-readable storage media having thereon computer-executable instructions that are structured such that, when executed by one or more processors of a computing system, cause the computing system to perform the following:

• generate, from user input received from a user of the computing system, an initial profile that specifies expected behavioral patterns of datasets that are to be received by the computing system;
• extract from one or more received datasets received by the computing system one or more features that are indicative of behavioral patterns of the one or more received datasets;
• provide the initial profile to one or more first machine-learning models, the one or more first machine-learning models having been trained using a subset of the one or more datasets, the one or more first machine-learning models using the initial profile to determine if the behavioral patterns of the received datasets are anomalous;
• and
• at one or more second machine-learning models that have been trained using a subset of the one or more datasets, train a second profile based on the one or more features to specify behavioral patterns of the received datasets that are learned by the second machine-learning model.