Abstract: A method of managing execution of a secure application is disclosed. The method comprises receiving an initial profile of an wireless communication device (WCD) by a secure application manager executing on a computer system, storing the initial profile by the secure application manager in a datastore; receiving a request comprising a current profile of the WCD by the secure application manager from an API of a secure application executing on the WCD to invoke an operation of a secure application; comparing the current profile of the WCD by the secure application manager to the initial profile of the WCD stored in the immutable record in the datastore; and in response to determining that the current profile of the WCD matches the initial profile of the WCD, passing the request to invoke an operation of the secure application by the secure application manager to the secure application for execution.

Abstract: Aspects of the disclosure relate to machine learning based automated management of a user account. A computing platform may determine, via a computing device and based on historical user activity of a user, a pattern of the user activity. Subsequently, the computing platform may detect a deviation from the pattern of the user activity. Then, the computing platform may identify an anticipated transaction of the user. Then, the computing platform may retrieve, from a repository of user data, one or more user-defined preference rules associated with the anticipated transaction. Then, the computing platform may determine whether the one or more preference rules apply to one or more attributes of the anticipated transaction. Subsequently, the computing platform may trigger, based on a determination that the one or more preference rules apply to the one or more attributes of the anticipated transaction, an action associated with the anticipated transaction.

Abstract: Systems, methods, and computer program products are provided herein for hyperspectral imaging based authentication. An example method includes receiving check data associated with at least a first user and extracting one or more field details from the check data. By leveraging a hyperspectral imaging module, the method further includes generating hyperspectral image data associated with the one or more extracted field details and determining one or more spectral characteristics associated with the one or more extracted field details based on the hyperspectral image data. The method further includes determining a tampering indication for the check data based on the one or more spectral characteristics. The spectral characteristics may include one or more reflectance values associated with extracted field details across a plurality of spectral bands.

Abstract: An automatic bidding system includes a vehicle agent (a computer). A vehicle agent includes a bidding agent (a bidding unit) that places an automatic bid for power trading related to electric power of a user in accordance with an automatic bidding algorithm, and an information collection agent (an information collection unit) that acquires user information indicating a preference of the user. The bidding agent is configured to set a parameter of the automatic bidding algorithm using the user information.

Abstract: A transaction tracking service (TTS). The TTS includes a transaction repository configured to store transaction records organized within a transaction groups. The TTS also includes a computer processor operatively connected to the transaction repository. The computer processor is configured to execute instructions to make a first determination that a first transaction record of the plurality of transaction records is unassigned, generate, based on the first determination, an unassigned transaction list (UTL) comprising a first set of transaction data associated with the first transaction record, and transmit the UTL to a client device operatively connected to the TTS.

Abstract: Aspects described herein may use a machine learning model to identify transactions likely to be remembered by a user and that may be used to generate challenge questions to authenticate the user. An individual may request an action related to a financial account. In response to the request, the machine learning model may determine a likelihood an authorized user of the financial account will remember one or more recent transactions. The likelihood of each candidate transaction may be compared to a predetermined threshold to determine a subset of recent transactions. Information relating to the subset of recent transactions may be used to generate one or more challenge questions to pose to the user. The user's responses to the challenge questions may be used to evaluate whether the user is the authorized user of the financial account or is a fraudster or imposter.

Abstract: Techniques are disclosed relating to a graphical user interface (GUI) for editing classification rules. The graphical user interface may include a display of a modified threshold value for a classification rule, where values on one side (e.g. above) the threshold value indicate a first type of classification, and values on the other side (e.g. below) indicate a second type of classification. Machine learning techniques may be used to suggest a modified threshold value to the user, who may accept the modified value, or may provide, via the GUI, their own modified value, which can be different from a suggested value. Graphical indications of accuracy for the classification rule may be displayed.

Abstract: An apparatus for receiving user metrics related to a user. The apparatus is configured to identify a plurality of sets of protocol parameters related to a plurality of contingent payments. Apparatus is configured to determine an efficiency score of each of the contingent payments as a function of the plurality of protocol parameters and an efficiency criterion. Apparatus is configured to select a first contingent payment of the plurality of the contingent payments as a function of the efficiency score, wherein the first contingent payment comprises a first set of protocol parameters of the plurality of parameters. Apparatus is configured to generate an optimization model of the first contingent payment as a function of the user metrics and the first set of protocol parameters, wherein the optimization model comprises one or more regulatory elements.

Abstract: There are provided systems and methods for flexible digital tokens with application programming interfaces for reduced computing calls. A service provider, such as an electronic transaction processor for digital transactions, may provide a processing system, stack and API that allows for generation of flexible payment tokens that can be used for electronic transaction processing with external service providers including social networking platforms and services. The processing system for the transaction processor may include an API in a compatible language with the APIs of the external service providers. Specific API calls and queries, which may correspond to GraphQL mutations, may be used to execute operations between the APIs of the interfacing systems to have a legacy processing system and API to generate a billing agreement. Once generated, the billing agreement may be tokenized, and a payment token used for payment processing.

Abstract: A system may receive a first resource allocation request (associated with a first company) from a first entity. The system may determine that the first request is not associated with a risk relationship and arrange for it to be processed via a claim servicing entity. Information about the first request may then be routed to a request handler device for processing and a communication with a first graphical indication may be generated. The system may also receive a second resource allocation request (associated with the first company) from a second entity and determine that it is to be processed via a risk. The system may then route information about the second request to a request handler device for processing and generate a communication with a second graphical indication. Note that the request handler device may be the same device that received the information about the first request.

Abstract: Systems, methods, and apparatuses for automatically detecting the risk of dealer default are described. A machine learning model may be trained using a gradient boosting technique on a dataset that includes historical lien information, historical dealer information, and historical vehicle default information. Lien information and financing information for vehicles may be received and correlated. Furthermore, a machine learning model may generate aggregate risk scores for dealers. Furthermore, determination of an aggregate risk score that exceeds a threshold risk score may cause the generation of a notification.

Abstract: A system and computer-implemented method of continuously updating information about one or more of a customer approved for a mortgage and a real estate property identified as mortgage ready. The method includes monitoring information accessed from a memory storage location corresponding to a customer identification number, the information used to determine the customer is approved for a mortgage, and receiving new information about the customer, the new information used to determine the customer is approved for a mortgage. The method also includes updating, at a memory coupled to the one or more processors, the memory storage location to include the new information. The method still further includes recalculating the amount in which the customer is approved for a mortgage based upon the new information received.

Abstract: According to an aspect, a technology system maintains an account data specifying the details of multiple accounts including a specific set of accounts as being delinquent. Upon receiving a feature set to be used, the system clusters the multiple accounts into groups based on the feature set. The system generates a multi-classification model for assignment of agents to the accounts based on the group qualifiers associated with the groups and the feature set. The system then identifies a target group likely to present problems with debt collection, assigns, using the multi-classification model, a corresponding agent for each account of the group and determines a recommended recovery strategy for each assignment. The system provides the details of the group, the corresponding agents assigned and the recommended recovery strategy for each assignment.

Abstract: Systems and methods for generating tree-based models with improved fairness are disclosed. The disclosed process generates a first tree-based machine learning model, which is preferably trained to predict if a financial loan will be repaid. The process also determines an accuracy of the first tree-based machine learning mode. In addition, the process determines a fairness of the first tree-based machine learning model. The fairness is preferably associated with at least one of gender, race, ethnicity, age, marital status, military status, sexual orientation, and disability status. The process then generates a second different tree-based machine learning model, which is preferably trained based on the accuracy of the first tree-based machine learning model and the fairness of the first tree-based machine learning model. The process then combines the first tree-based machine learning model and the second tree-based machine learning model to produce a gradient-boosted machine learning model.

Abstract: A method for asset evaluation and funding includes receiving, in a server, a request from a client device to access a digital item associated with an asset. The method also includes collecting a personal information of a user associated with the asset, assessing a status of the user based on the personal information, and collecting a historical information associated with similar users and similar assets. The method includes searching for values of the asset in a network, determining attributes of the digital item based on the value of the asset, the status of the user, and the historical information, and generating documents for the user, wherein collecting a personal information associated with the user comprises searching for a first information from a third party database, and requesting a second information from the user. A system and a non-transitory, computer-readable medium storing instruction to perform the above method are also provided.

Abstract: A method including training a machine-learning model, based on historical data, with a maximization problem and one or more minimization problems to improve one or more fairness metrics. The method also can include receiving real-time data. The method additionally can include generating a risk score based on the machine-learning model, as trained, and the real-time data. Other embodiments are described.

Abstract: A method of deriving a financial conscientiousness score from visual choices, using a machine learning model that is trained at a server is provided. The method includes (i) obtaining visual selection as an input from the user that is selected from one or more different visual choices that are displayed to the user, (ii) determining trait scores for a subset of traits based on the points that are attributed to the visual choices, (iii) training, a machine learning model by correlating the trait scores for the subset of traits with a previous credit history or a loan repayment record of the user to obtain a trained machine learning model, and (iv) determining, using the trained machine learning model, a financial conscientiousness score based on the trait scores for the subset of traits.

Abstract: In some implementations, a credit decision platform may receive a credit request from an applicant and obtain domestic historical data associated with the applicant from a credit bureau device. The credit decision platform may obtain access to an email account associated with the applicant based on determining that the domestic historical data associated with the applicant is insufficient to process the credit request. The credit decision platform may identify, using one or more machine learning models, a set of email messages included in the email account that are relevant to the credit request and may analyze content included in the set of email messages to generate non-domestic historical data associated with the applicant. The credit decision platform may generate a decision on the credit request based on an estimated creditworthiness of the applicant, which may be determined based on the non-domestic historical data.

Abstract: A computerized-method for predicting a probability of fraudulent financial-account access, is provided herein. The computerized-method includes a. building a Machine Learning (ML) sequence model; b. implementing a forward-propagation-routine in an encapsulated environment that runs applications to mimic a process of the ML sequence model. The forward-propagation-routine is mimicking processing of a chronical-sequence of a preconfigured number of non-financial activities sequence vector, layer by layer to generate a fraud probability score and using weights and biases which were extracted from each layer of the trained ML sequence model; and c.

Abstract: Prescreened electronic programs or products that are automatically determined for a specific potential entity based on characteristics and/or geographic location, then can be automatically ranked based on calculated expected values of respective programs or products. The ranked programs or products are digitally/electronically presented in an interactive graphical user interface to the specific entity for digital selection and application.