Abstract: In one embodiment, the present disclosure includes a method for determining a location of a user. In one embodiment, the method includes receiving operation data including character fields and a first identifier. A query that includes the first identifier is sent to a data store. In response to the query, operation types and corresponding count values are received. Character fields from the operation data are converted into tokens. For each of the tokens, a likelihood value and a second identifier specifying a respective machine learning parameter is retrieved. A machine-learning algorithm is configured based on the count values, and the likelihood values and specified parameters are processed by the configured machine-learning algorithm to determine whether the operation data corresponds to the geographic location of a user.

Abstract: In one embodiment, the present disclosure includes a method for determining a location of a user. In one embodiment, the method includes receiving operation data including character fields and a first identifier. A query that includes the first identifier is sent to a data store. In response to the query, operation types and corresponding count values are received. Character fields from the operation data are converted into tokens. For each of the tokens, a likelihood value and a second identifier specifying a respective machine learning parameter is retrieved. A machine-learning algorithm is configured based on the count values, and the likelihood values and specified parameters are processed by the configured machine-learning algorithm to determine whether the operation data corresponds to the geographic location of a user.

Abstract: In one embodiment, the present disclosure pertains to dynamically generating normalized master data. In one embodiment, input records comprising string representations of entities are received from multiple sources. The input records may be used as queries to a similarity search data store of master data records. One or more most likely matching master records are returned with corresponding similarity scores. The input record, master record, and a training set are processed using a machine learning algorithm. In one embodiment, one or more similarity scores are incorporated into the machine learning algorithm. The machine learning algorithm produces a final score. Data from input records may be merged into the master records if the final score is greater than a threshold.

Abstract: In one embodiment, the present disclosure pertains to data cleansing. In one embodiment, data cleansing is performed across a distributed master data store asynchronously in a scalable architecture, thereby allowing vast amounts of input records to be processed more efficiently.