Abstract: The subject technology receives an input data set including rows of values for features of the input data set, each row including a different combination of values for the features. The subject technology classifies one or more rows of values as an anomaly based on anomaly scores determined for each of the rows of values. The subject technology determines a subset of the different features that affect the anomaly scores of the one or more rows classified as the anomaly. The subject technology determines a root cause for at least one of the rows classified as the anomaly based on values of the subset of the different features for the at least one of the rows. The subject technology provides an indication of the root cause to a device to enable the device to perform an action when encountering conditions corresponding to the root cause at a subsequent time.

Abstract: One or more techniques and/or systems are provided for inferring user intent and/or for inferring a user location type of a user based upon venue boundary evaluation. For example, a user is located at a current user location, such as a downtown district of a city. One or more venue evaluation boundaries, corresponding to areas around the current user location, may be defined. Potential user intents, corresponding to venue types of venues within a venue evaluation boundary, may be identified (e.g., a buy coffee intent, a go to theatre intent, a meet a friend for lunch, intent, etc.) and may be assigned user intent values (e.g., the meet a friend for lunch intent may be assigned a lower value due to a current time being 9 am). Venue evaluation boundaries may be evaluated until an inferred user intent and/or inferred user location type (e.g., commercial, residential, etc.) is identified.