Inventions

A widely used measure of financial risk is Value at Risk (VaR), which estimates the maximum expected loss over a specified period at a given confidence level. 

Traditionally, VaR has been calculated using three main approaches: parametric models, historical simulation, and Monte Carlo simulation.

In 2022, we invented Generative Value at Risk (GVaR), which applies probabilistic ensemble machine learning to generateVaR measures seamlessly. 

See our presentation on GVaR given at the 2023 O'Reilly Media conference on Generative AI in Finance.

In 2005, long before machine learning became an industry buzzword, Deepak developed a probabilistic machine learning method and software system for managing the risks and returns of project portfolios. 

The system learned from data in time sheets and work‑completion percentages to continually update the probability that a project would remain within its time, budget, schedule, and resource constraints. This was done at project, program and portfolio levels.

It is a unique probabilistic framework that has since been cited in patents filed by IBM, Fujitsu, Accenture, Huazhong University of Science and Technology, State Grid Zhejiang Electric Power Co Ltd, Zhejiang Gongshang University, Kyung Hee University's Industry-Academia Collaboration Foundation. See the patent filing.