Manthan Sheth
Portfolio Researcher at Millennium
Bengaluru, Karnataka, India
Summary
👤
Senior🎓
Top SchoolManthan Sheth is a portfolio researcher and market-risk quantitative strategist with 11 years’ experience building multi-factor scenario and operational risk models across commodities, securitized products and mortgage assets. He has held progressive risk-strat roles at Goldman Sachs and now contributes enterprise risk research at Millennium, blending rigorous quantitative methods with production-ready software. An IIT Roorkee electrical engineering major with a computer science minor, he pairs CFA Level II and FRM Level I credentials with hands-on C++ and ML engineering work. His open-source contributions to mlpack — notably improving decision trees and adding neural net components like Batch Normalization — reflect a rare mix of low-latency quantitative modelling and practical ML implementation. Based in Bengaluru, he thrives at the intersection of math, finance and technology, with a demonstrated ability to translate complex financial products and stressed scenarios into auditable models. A curious NLP and developer enthusiast, he brings both research depth and engineering discipline to risk problems that influence firm-wide portfolios.
11 years of coding experience
5 years of employment as a software developer
Indian Institute of Technology Roorkee
English, Hindi, Gujarati, Marathi
Github Skills (10)
decision-tree10
machine-learning10
c-language10
cpp10
cprogramming-language10
cplus10
deep-learning9
regression9
python7
testing7
Programming languages (4)
Github contributions (5)
mlpack/mlpack
Mar 2018 - Apr 2018
mlpack: a fast, header-only C++ machine learning library
Role in this project:
ML Engineer
ML EngineerContributions:40 commits, 5 PRs, 98 comments in 1 month
Contributions summary:Manthan primarily contributed to the decision tree implementation within the mlpack library. Their commits focused on enhancing the decision tree functionality by adding parameters, fixing style issues, and adding tests for the command-line interface. They also worked on implementing the Batch Normalization layer and Flexible ReLU layer and added respective tests. These changes demonstrate a focus on improving the machine learning capabilities of the library.
regressionheaderdeep-learningscientific-computingc-plus-plus
Manthan-R-Sheth/DigiModel
Jan 2016 - Oct 2017
Contributions:21 commits, 1 PR, 16 pushes in 1 year 9 months
cardboardsensorsandroid-sensorsandroidhand
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.