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: A computer system that provides a low friction operator interface on a mobile device is disclosed. The computer system can comprise a mobile device processor and a mobile application. The mobile application is executable to present a graphical user interface at the mobile device, the graphical user interface comprising series of application pages having inputs for a limited set of user record information; receive the limited set of user record information via the user interface; enhance the limited set of user record information with personally identifiable information extracted from an image and send the enhanced set of user record information to a server for processing.

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.

Abstract: A computer system that provides a low friction operator interface on a mobile device is disclosed. The computer system can comprise a mobile device processor and a mobile application. The mobile application is executable to present a graphical user interface at the mobile device, the graphical user interface comprising series of application pages having inputs for a limited set of user record information; receive the limited set of user record information via the user interface; enhance the limited set of user record information with personally identifiable information extracted from an image and send the enhanced set of user record information to a server for processing.

Abstract: One embodiment comprises a rules-based data processing system. The rules-based data processing system can comprise a processor and a memory coupled to the processor storing a set of computer executable instructions. The rules-based data processing system can use pre-calculated payment schedules to automatically populate a requested electronic document. The rules-based data processing system communicates the electronic document to the mobile application for presentation in the operator interface of a mobile device. The rules-based data processing system can further comprise a data store storing a set of depreciation models, each depreciation model having an associated vehicle year/make/model/trim, and payment rules to determine payment schedules for vehicles using the set of depreciation models.

Abstract: A system comprising a server coupled to a data store storing a set of approval rules, a set of APIs specifically configured for a plurality of remote information data provider systems. The system comprising a mobile device comprising the mobile application executable to provide a low friction user interface to allow a user to enter a limited amount of personally identifiable information and an image of an identification document, enhance the limited amount of personally identifiable information with personally identifiable information extracted from the identification document to create an enhanced set of personally identifiable information. The server configured to approve a user application based on the enhanced set of personally identifiable information and other application data received from the mobile application. The server and mobile application cooperating to allow the user to complete a transaction via the server based on the approval.

Abstract: A rules/model-based data processing system that approves applications by users of the data processing system based on data from distributed sources. The system is configured to receive a request to approve a user application, access rules/models that fit the goal of approving the user application, obtain data from distributed sources, apply rules/models to generate processed data and determines if the obtained or processed data fits the rules. The system comprises a server configured to access the approval rules based on a request from a mobile application to approve the user application, the approval rules referencing information provider data from a remote information provider system. The server can connect to the remote information provider system to retrieve, using personally identifiable information from the user application, the set of information provider data referenced and approve the user application based on the application of the approval rules to the information provider data.