Walmart Apollo, LLC

Paypal, Inc.

Hui-Min Chen

Lian Liu

Sangita Fatnani

Vidhya Raman

Premalatha Thangamani

Uday Akella

Jingru Zhou

Tzu-Yen Wang

Yitao Yao

Pei Wang

Zhiping Tang

Vivek Crasta

Shihui Jia

James ZhiPing Tang

Chuying Ma

Ashley Renee Renee Greehey

David Andrew Splittorff

Catherine Antill

Jaya Kolhatkar

Kevin Philip Clay

Guoyu Zhu

Systems and methods for generating and using trained logit models using weight-of-evidence (WOE) based processes are disclosed. A training data set including sets of variables and a classification of each set in the sets of variables is received. The classification includes one of at least two potential classifications. A WOE feature set is generated by applying a binning process to each variable in the set of variables to generate one or more WOE transformations and applying the one or more WOE transformations to a corresponding variable in the set of variables. A trained logistic regression model is generated by applying an iterative training process based on the WOE feature set. The trained logistic regression model is configured to classify each set of variables. Production data sets are classified into one of the at least two potential classifications using the WOE transformations and the trained logistic regression model.

Systems and methods for weight of evidence based feature engineering and machine learning

This application relates to systems and methods for auditing registers. In some examples, a system comprises registers, a recycling device, handheld computing devices, and retailer computing devices. The retailer computing devices may be configured to store a decision model, receive a calculated monetary position and activity data for one of the registers, generate a first associate record based at least on the decision model and one or more of the calculated monetary position and the activity data, generate a second associate record based at least on the decision model and historical behavioral data for one or more associates, generate a first audit alert record based at least on the second associate record and the decision model, send audit alerts to the handheld computing devices, and send the first audit alert record to the database.

Systems and methods for auditing registers

This application relates to apparatus and methods for identifying fraudulent transactions. A computing device receives return data identifying the return of at least one item. The computing device obtains modified strategy data identifying at least one rule of a modified strategy. The rule may be based on the application of at least one discrete stochastic gradient descent algorithm to an initial strategy. The computing device applies the modified strategy to the received return data identifying the return of the at least one item, and determines whether the return of the at least one item is fraudulent based on the application of the modified strategy. The computing device generates fraud data identifying whether the return of the at least one item is fraudulent based on the determination, and may transmit the fraud data to another computing device to indicate whether the return is fraudulent.

Methods and apparatus for fraud detection

This application relates to apparatus and methods for identifying fraudulent transactions. A computing device receives return data identifying the return of at least one item. The computing device obtains modified strategy data identifying at least one rule of a modified strategy. The rule may be based on the application of at least one dimensionality reduction algorithm to an initial strategy. The computing device applies the modified strategy to the received return data identifying the return of the at least one item, and determines whether the return of the at least one item is fraudulent based on the application of the modified strategy. The computing device generates fraud data identifying whether the return of the at least one item is fraudulent based on the determination, and may transmit the fraud data to another computing device to indicate whether the return is fraudulent.

This application relates to systems and methods for automatically generating fraud strategies. A system may comprise customer computing devices, a database, and retailer computing device(s). The retailer computing device(s) are configured to receive data related to customer transactions, calculate a negative reaction score, negative resolution score, anomaly score, and impact score for at least one value of the received data, determine whether the calculated scores are greater than or equal to respective thresholds, identify a value of the received data as a potentially fraudulent data value when one or more of the calculated scores is greater than or equal to its respective threshold, generate an output comprising a list of potentially fraudulent data value(s) and impact scores, identify area(s) of high impact leaks based on the output, and determine which customer computing devices are executing fraudulent transactions based on the identification of areas of high impact leaks.

Systems and methods for automatically generating fraud strategies

This application relates to apparatus and methods for identifying anomalies within a time series. In some examples, a computing device receives sales data identifying a sale of at least one item, and aggregates the received data in a database. The computing device may generate a plurality of time series based on the aggregated sales data. The computing device may extract features from the plurality of time series, and generate an alerting algorithm that is based on clusters of the extracted features. The computing device may apply the alerting algorithm to a time series generated from received sales data to determine whether the time series is an anomaly. Based on the determination, the computing device may generate and transmit anomaly data identifying whether the time series is an anomaly, such as to another computing device.

Methods and apparatus for anomaly detections

A method and system for identifying and labeling fraudulent store return activities includes receiving, by a server, retailer events from an online transaction system of a retailer, the retailer events comprising records of transactions between customers and the retailer, including sale, exchange and return activities across multiple stores. The retailer events are processed to build a network that associates stores, transactions, payment instruments, and customer identification over related activity sequences of transactions. Return fraud labels are generated for the retailer events representing returns based on identified fraud characteristics of the related activity sequences by: representing behavior variables extracted from activity sequences by respective signature vectors; calculating pairwise similarity between the signature vectors; identifying clusters of the signature vectors having common behavior patterns based on the calculated pairwise similarity; and labeling the identified clusters of signature vectors as non-fraudulent behavior or fraudulent behavior.

Identifying and labeling fraudulent store return activities

Aspects of the present disclosure involve a system and method for learning from images of raw data, including transactional data. In one embodiment, a system is introduced that can learn from the images of such data. In particular, machine learning is implemented on images in order to classify information in a more accurate manner. The images are created from raw data deriving from data sources relating to user accounts, in various embodiments.

System and method for learning from the images of raw data

Aspects of the present disclosure involve a system and method for learning from images of transactional data. In one embodiment, a system is introduced that can learn from the images of transactional data. In particular, machine learning is implemented on images in order to classify information in a more accurate manner. The images are created from raw data deriving from a user account.

Growing community of inventors

Pleasanton, CA, United States of America

Hui-Min Chen