Abstract: A system for building, training and productionizing machine learning models is disclosed. A model training specification is received, and a plurality of sets of hyper-parameters is obtained. Sets of training data and hyper parameter sets are distributed to distributed training systems. Models are trained in parallel using different sets of training data. Models are trained using multiple sets of hyper parameters. A candidate hyper-parameter set is selected, based on a measure of estimated effectiveness of the trained predictive models, and a production predictive model is generated by training a predictive model using the selected candidate hyper-parameter set and the complete set of training data.

Abstract: Systems, methods and products in which a neural network is trained with a set of feed records constructed using information from both item-specific records and item type records to generate a self-defined vector space in which vehicle characteristic vectors can be defined. The trained neural network then generates a vehicle characteristic vectors for each of a set of inventory records. Consumer usage data is collected and a vehicle of interest is identified. A vehicle characteristic vector encoding the vehicle of interest is generated, and is used to compute a dot product as a similarity score for each inventory record's vehicle characteristic vector. The scores corresponding to the different inventory records are ranked, and a notification is provided to the consumer identifying inventory records that are similar to the vehicle of interest.

Abstract: An embodiment includes executing a machine learning risk prediction model representing a set of credit report data features and a default label space associated with transactions via a data processing system; receiving a request to approve an electronic application for a user; storing credit report data for the user in a user record; extracting a set of credit report data attributes from the user record; creating a feature vector comprising features representing the set of credit report data attributes extracted from the user record; determining a predicted default risk score for the user, comprising processing the feature vector using the machine learning risk prediction model; and updating the first user record for the first user by adding the predicted default risk score to the first user record, wherein the predicted default risk score is used by a data processing system to control an online application approval process.

Abstract: An embodiment provides a data processing system comprising a processor coupled to a memory for storing a machine learning current value model trained to output a prediction of current value, the machine learning current value model representing a set of vehicle features and historical secondary market transaction values. The processor is configured to create a set of inventory records. The processor is further configured to extract a set of vehicle attributes for a respective vehicle from an inventory record, create a feature vector for the respective vehicle based on the set of vehicle attributes extracted from the inventory record, determine a current value for the respective vehicle by processing the feature vector for the respective vehicle using the machine learning current value model and update the inventory record for the respective vehicle by adding the current value for the respective vehicle to the inventory record for the respective vehicle.

Abstract: A system for building, training and productionizing machine learning models is disclosed. A model training specification is received, and a plurality of sets of hyper-parameters is obtained. Sets of training data and hyper parameter sets are distributed to distributed training systems. Models are trained in parallel using different sets of training data. Models are trained using multiple sets of hyper parameters. A candidate hyper-parameter set is selected, based on a measure of estimated effectiveness of the trained predictive models, and a production predictive model is generated by training a predictive model using the selected candidate hyper-parameter set and the complete set of training data.