© Hedged Capital LLC. All Rights Reserved.


In 2005, long before machine learning was an industry buzzword, Deepak invented a probabilistic machine learning method and system for managing the risks and returns of project portfolios. It is a unique framework and has been cited in patents filed by IBM (twice), Accenture, Fujitsu, Huazhong University of Science and Technology, State Grid Zhejiang Electric Power Co Ltd, Zhejiang Gongshang University, Kyung Hee University's Industry-Academia Collaboration Foundation among others. See patent filing here .

​

​​​​PUBLICATIONS AND TRAINING COURSES ​​

​​​​

​Probabilistic Machine Learning for Finance and investing: A Primer to Generative AI with Python
  • Book informs the thinking practitioner about the profound flaws in modern statistics, financial theory, and conventional AI models, and explains why probabilistic ML, with its generative ensembles, proves useful in domains where participants express emotions, creativity, and free will.
  • Github repository of notebooks with Python code used in the book.

​Generative Value at Risk (GVaR)
  • ​Presentation summarizes our new method of estimating VaR using generative ensembles. Part of a discussion on Generative AI for Finance hosted by O'Reilly.

Hands-on Algorithmic Trading with Python

  •  Video course explains the concepts, process, and technological tools for developing algorithmic trading strategies using Python libraries. Interactive quiz tests your understanding of the content. Published by O'Reilly Media.


The Trinity Of Errors In Financial Models: An Introductory Analysis Using TensorFlow Probability

  • Article explores the trifecta of errors that are endemic in all financial models. Published on Google's TensorFlow Probability blog.


The Trinity of Errors in Applying Confidence Intervals: An Exploration Using Statsmodels

  • Article provides the three reasons why confidence intervals should not be used in financial data analyses. Published on O'Reilly Media's blog.