a computer processor; and

a non-transitory computer-readable storage medium storage having instructions that when executed by the computer processor perform actions comprising:

predicting, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period, the first machine learning model trained using historical frequency data for an average number of claims from a prior time period and training further performed based on a segment type defining a type of claim being submitted, each type of segment having corresponding peril types further defining the type of claim;

predicting, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data including an average loss severity value of each claim for the prior time period and based on the segment type and the corresponding peril types;

determining the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model; and,

wherein the first and the second machine learning model, once trained for each of the types of segments and thereby trained for different peril types are applied for predicting a subsequent expected loss for subsequent claims associated with any one of the peril types for each segment type of claim.