This inventor holds 5 USPTO granted patents and 4 published patent applications and 1 EPO patent. Top assignee: Visa International Service Association. Active years: 2023-2026.
Company Filing History:
Years Active: 2023-2026
Title: Mangesh Bendre: Innovator in Anomaly Detection and Node Embeddings
Introduction
Mangesh Bendre is a notable inventor based in Sunnyvale, CA, who has made significant contributions to the fields of anomaly detection and machine learning. With a total of three patents to his name, Bendre's work focuses on enhancing data processing techniques through innovative methodologies.
Latest Patents
Bendre's latest patents include a method, system, and computer program product for synthetic oversampling aimed at boosting supervised anomaly detection. This invention formulates an iterative data mix-up problem into a Markov decision process (MDP) with a tailored reward signal to guide the learning process. To solve the MDP, a deep deterministic actor-critic framework is modified to adapt a discrete-continuous decision space for training a data augmentation policy. Another significant patent involves systems, methods, and computer program products for generating node embeddings. This system includes at least one processor programmed to generate a graph comprising multiple nodes, create an embedding for each node, and convert these embeddings to Cartesian coordinates in response to processing the graph with a machine-learning algorithm.
Career Highlights
Mangesh Bendre is currently employed at Visa International Service Association, where he applies his expertise in machine learning and data analysis. His innovative approaches have contributed to advancements in the financial technology sector, particularly in enhancing transaction security and efficiency.
Collaborations
Bendre has collaborated with talented coworkers such as Hao Yang and Mahashweta Das, contributing to a dynamic work environment that fosters innovation and creativity.
Conclusion
Mangesh Bendre's contributions to the fields of anomaly detection and node embeddings highlight his role as a leading inventor in technology. His patents reflect a commitment to advancing machine learning methodologies, making a significant impact in his field.