Abstract: Various methods and processes, apparatuses or systems, and media for performing fairness aware optimization are disclosed. The present disclosure provides acquiring and quantizing a plurality of input features for an application, and binning of each of the plurality of input features quantized so that each of the plurality of input features is assigned to a bin among a plurality of bins to provide a matrix of bin membership for each of the plurality of applications. A vector is then generated based on the matrix of bin membership for evaluating the generated vector against a target value and presence of disparity in outcome for a protected input feature. Once a coefficient vector that optimizes an output while negating any disparity in outcome for the protected input feature is identified, an optimization model is updated with such coefficient vector for subsequent processing.

Abstract: Various methods and processes, apparatuses or systems, and media for mitigating disparities between outputs of different AI/ML models that are subject to usage constraints are disclosed. The method includes: receiving uncertainty values and model quality-related parameter values that are associated with at least two models that are configured to generate a loan price for a loan applicant; receiving feature weight functions that relate to weights of target metrics; calculating model weights for each model; selecting a customized model based on the model weights; receiving a tabular set of personal data that includes individualized financial information and individualized demographic information associated with loan applicants; training the customized model by using the tabular set of personal data, the target metrics, a set of sensitive labels, and historical information that relates to outputs generated by the models; and using the trained model to generate a customized loan price for a loan applicant.

Abstract: Various methods and processes, apparatuses/systems, and media for constrained and loan pricing are disclosed. An optimization engine provides daily pricing vector for each loan pricing segment. The daily pricing output per segment (“vectors”) flows into an assessment process to determine a profit and loss (PnL) calculation and a constraints score. The resulting vectors (along with the PnL calculation and constraint scores) are stored in a tuple store. A processor updates surrogate parameters with new tuple store data points; evaluates an acquisition function on the surrogate parameters to find the next query subsidy vector; utilizes this expanded set of vectors and runs them back through the PnL calculation and generates constraint scores; and reports sufficiently subsidy vectors to a pricing team for final subsidy selection.

Abstract: A client server system (100, 200, 300) comprises a client subsystem (100), a server subsystem (200) and an interconnecting data network. The client subsystem includes a client application (110, 120, 130, 140, 150) operable to initiate a secure connection over the interconnecting network with the server subsystem (200). The server subsystem includes a server application (254, 255, 256, 257), which is operable to co-operate with the client application to complete the setting up of a secure connection with the client application upon initiation of the connection by the client application and which is further operable to transmit output data over such a connection in response to requests for service provided by the client application.

Abstract: A client-side intermediary (30) is provided to balance the loading of Web service requests between a plurality of servers (32). The status of the Web service servers (32) is monitored by a monitoring server (35) which provides status updates to the intermediary (30) upon request. The intermediary then uses the information on the status of the servers (32) to decide where to send web service requests. Additionally, the intermediary is able to direct requests for Web service descriptions to the least busy server on the basis of status information. The intermediary (30) substitutes its own identifier for the service name and port in the Web service description before passing it to the client so that all requests are directed through it, thus allowing the continual provision of service for the client even in the event that one of the servers fails.