Yodlee, Inc.

Deepak Chandrakant Patil

Om Dadaji Deshmukh

Atif Adib

Rakesh Kumar Ranjan

Rahul Mitra

Vinay Manjunath

Gaurav Singhal

Shibsankar Das

Karishma Dahal

Siddhartha Saxena

Rushikesh Rathod

As described herein, a system, method, and computer program are provided for synthesizing user transactional data for de-identifying sensitive information. In use, transactional data of a plurality of users is identified. Additionally, the plurality of users are clustered based on the transactional data, to form groups of users having transactional data representing similar transactional behavior. Further, synthesized transactional data is generated for the users in each group by: identifying a subset of the transactional data that corresponds to the users in each group, shuffling the transactional data in the subset across the users in each group, and perturbing portions of the shuffled transactional data.

Synthesizing user transactional data for de-identifying sensitive information

As described herein, a system, method, and computer program are provided for context-based data-driven classification. Input to be processed using a classifier is identified. Data is obtained from one or more third party data sources, based on the input to be processed. The input is processed, using the classifier, to generate output that includes at least one classification for the input. Both the data from the one or more third party data sources and the output of the classifier are processed to determine a final classification for the input.

System, method, and computer program for a context-based data-driven classifier

Methods, systems and computer program products generating diverse and representative set of samples from a large amount of transaction data are disclosed. A data sampling system receives transaction records. Each transaction record has multiple text segments. The system selects a subset of transaction records that contain least frequently appeared text segments. The system determines a respective vector representation for each selected transaction record. The system can measure similarity between transaction records based on the vector representations. The system assigns the selected transaction records to multiple clusters based on the vector representations and designated dimensions of importance. The system identifies one or more anchors that include transaction records on boundaries between clusters. The system filters the subset of transaction records by removing transaction records that are close to the anchors. The system then provides the filtered subset as a representative set of samples to a sample consumer.

Generating samples of transaction data sets

Growing community of inventors

Dombivli, India

Deepak Chandrakant Patil