Abstract: A system comprising at least one hardware processor; and a non-transitory computer-readable storage medium having stored thereon program instructions, the program instructions executable by the at least one hardware processor to: receive a test dataset comprising data associated with test dataset of a machine learning model applied to target data, generate a set of expected values associated with the test dataset, and analyze the test dataset, based, at least in part, on the set of expected values, to detect a variance between the test dataset and the set of expected values, wherein the variance is indicative of an accuracy parameter of the machine learning model.

Abstract: Techniques for providing interactive visualizations for an entity or group of entities based on search interest data are provided. The search interest data may be derived from Internet or online search data related to the entities and relevant attributes of the entities. Each of the entities and attributes may be represented in a structured search market using a predefined list of relevant search terms or keywords. The search interest of each entity and attribute may be determined based on probabilities representing a likelihood of a search for an entity co-occurring with a search for a relevant attribute within a predetermined time proximity.