A method for mobile credit acquisition is disclosed. The method deploys a shopping incentive offer, the shopping incentive offer for a shopping incentive. A device identifier associated with a user's mobile device is received in response to a user responding to the shopping incentive offer on the user's mobile device. In addition, a user identifier is received for the user. The device identifier and the user identifier are used to obtain user specific information useable for a credit prescreen. The shopping incentive is then provided to the user's mobile device. If the user does pass a credit prescreen, a pre-approved credit offer is also provided to the user via the user's mobile device in conjunction with the shopping incentive.

A method for mobile credit acquisition is disclosed. The method deploys a shopping incentive offer, the shopping incentive offer for a shopping incentive. A device identifier associated with a user's mobile device is received in response to a user responding to the shopping incentive offer on the user's mobile device. In addition, a user identifier is received for the user. The device identifier and the user identifier are used to obtain user specific information useable for a credit prescreen. The shopping incentive is then provided to the user's mobile device. If the user does pass a credit prescreen, a pre-approved credit offer is also provided to the user via the user's mobile device in conjunction with the shopping incentive.

A network system for providing one or more services to one or more end-user devices communicatively coupled to the network system over a wireless access network, the network system comprising: a policy enforcement function, a first policy element, a second policy element, and a network element, wherein the network element is communicatively coupled to the policy enforcement function, the first policy element, and the second policy element, and wherein the network element is configured to communicate first policy information between the policy enforcement function and the first policy element, and communicate second policy information between the first policy enforcement function and the second policy element.

To detect multiple suspicious patterns while at the same time keeping the number of model parameters low, a learned aggregation model is used to distinguish suspiciously similar applications from unrelated applications.

A system for classifying to apply for a microloan by a user is provided. The system includes user device associated with a user, and loan applying user classification system. The loan applying user classification system 106 collects raw data from at least one of (i) one or more programs on the user device directly; (ii) the one or more programs indirectly through the network or (iii) both. The raw data includes mobile brand, screen height, demographic details, mcc, session timestamp, sessionid, session duration, etc. The loan applying user classification system is configured to (i) pre-process the raw data to obtain pre-processed data; (ii) identify representative set of features (i.e. training dataset) from the pre-processed data; (iii) balance an imbalanced training dataset to obtain balanced dataset; and (iv) generate a classification model using balanced dataset to classify in applying for micro-loan by the user.

Systems, methods, and computer program products are provided for increasing the return from a pool of loans for a company involved in the guarantee and securitization of such loans. In one exemplary embodiment, a computer-implemented method comprises creating a plurality of sub-pools in which to place loans from the pool of loans; determining, using one or more processors, an external value assessment for one or more loans from the pool and an internal value assessment for the one or more loans; identifying a difference between the external and internal value assessments; and selecting a sub-pool from the plurality of sub-pools to place the one or more loans based upon the identified difference.

A model variable candidate generation device generating explanatory variable candidates to be used as candidates for an explanatory variable in generation of a prediction model includes: a data input unit inputting analysis data each entry having one or more items and the items having item values; a first item determination unit preliminarily setting properties of the items included in the analysis data as first item properties; a data property determination unit determining data properties being of the analysis data on the basis of the first item properties; a second item determination unit determining properties of the items included in the analysis data as second item properties on the basis of the data properties of the analysis data; and a variable candidate generation unit generating the explanatory variable candidates by selecting from the items or processing the items on the basis of the second item properties.

An information processing system, method, and computer-readable medium that generate emotion values based on information related to interactions between one of a plurality of objects and other ones of the plurality of objects, the one of the plurality of objects being associated with a person, acquire at least one emotion value of the generated emotion values based on an identification of the person, and provide personal credit information of the person based on the acquired at least one emotional value.

Certain aspects of the present disclosure provide techniques for training predictive risk models based on user transaction history. An example method generally includes extracting, from a transaction history data set for a plurality of users of a software application, a plurality of features for each user of the plurality of users having records in the transaction history data set. A training data set is generated based on the extracted plurality of features for each user of the plurality of users. A plurality of predictive risk models is trained to generate a risk propensity score indicating a likelihood that a specified event will occur based on the training data set. Generally, monotonicity of one or more constraints is implemented in the model.

Certain aspects of the present disclosure provide techniques for training predictive risk models based on user transaction history. An example method generally includes extracting, from a transaction history data set for a plurality of users of a software application, a plurality of features for each user of the plurality of users having records in the transaction history data set. A training data set is generated based on the extracted plurality of features for each user of the plurality of users. A plurality of predictive risk models is trained to generate a risk propensity score indicating a likelihood that a specified event will occur based on the training data set. Generally, monotonicity of one or more constraints is implemented in the model.