Abstract: Techniques are described for identifying an input training dataset stored within an underlying data platform; and transmitting instructions to the data platform, the instructions being executable by the data platform to train a predictive model based on the input training dataset by delegating one or more data processing operations to a plurality of nodes across the data platform.

Abstract: Techniques are described for identifying an input training dataset stored within an underlying data platform; and transmitting instructions to the data platform, the instructions being executable by the data platform to train a predictive model based on the input training dataset by delegating one or more data processing operations to a plurality of nodes across the data platform.

Abstract: A method of and a system for generating a dataset from data stored in at least one data base, for input into an analytical model. The method comprises the steps of: defining a time stamped population comprising a plurality of tuples, each tuple comprising an entity identifier of an entity for analysis, and at least one reference time stamp associated with the corresponding entity identifier; and creating a dataset by generating at least one time dependent attribute value for each entity identifier from data associated with said entity identifier in the at least one database, the or each time dependent attribute value representing a time dependent parameter of the corresponding entity identifier and being generated according to a corresponding attribute definition, wherein the or each time dependent attribute value is generated as a function of the corresponding time stamp.