Abstract: A recommendation system includes a recommendation model for generating a recommendation score for a user with respect to an item. The model is configured to receive a set of dense features, describing numerical information, and a set of sparse features, representing a subset of items from a relatively large group of items. To represent the subset of items in the sparse features, each item (or a symbol thereof) is processed by an encoder to represent each item with a plurality of positions in a sparse binary representation of the subset of items. The sparse binary representation is then processed by a model that determines a vector representation of the sparse category features used in the prediction in conjunction with the dense features.

Abstract: A computerized method and system for creating test items by generating variants from a test item model, comprising the steps of creating a new test item model by identifying elements of an initial test item or test item model to be variabilized, variabilizing the elements thereby creating test item variables, indicating values the variables can assume, defining the variables, and generating test item variants utilizing a simultaneous constraint solver. The initial test item can be a pre-existing test item or test item model, a newly created test item or even a conceptual template in the mind of the test item creator. The generated test item variants are displayed to the test item creator. The test item creator can store and forward acceptable test item variants for later use as test items. Test item models can be stored for later use in generating new test item variants.