Dr. Narayan Ganesan is a quantitative analyst at Wells Fargo working on Capital Markets Pricing and Risk Modeling, in particular, models for equity, FX, interest rate derivatives and counterparty credit risk. Previously he was at Morgan Stanley’s Institutional Securities Technologies division, prior to joining which he was an Assistant Professor at Stevens Institute of Technology in the ECE department where his research specialized in High Performance computing platforms. He received his Ph.D in Electrical and Systems Engineering from Washington University in St. Louis and is a recipient of NJ inventors Hall of Fame award.
This paper presents a novel and direct approach to solving boundary- and final-value problems, corresponding to barrier options, using forward pathwise deep learning and forward–backward stochastic differential equations.
This paper discusses several methods to estimate fVaR or margin requirements and their expected time evolution, from simple options to more complex interest swaps.