Abstract: 

In finance, pricing options involves computationally intensive numerical methods like PDE solvers and Monte Carlo simulations. These numerical methods are used to compute the option prices as well as the ""greeks"" which are the derivatives of the option prices w.r.t to inputs like stock price (delta), volatility (vega) etc.

In this talk, we will look at how deep learning techniques can be used for building fast option pricers. A large set of representative training data is generated by using the numerical pricers. Then deep neural networks are used to learn the non-linear pricing functions.

Back propagation can be used to not only train the network (by updating the weights using gradient descent) but also to compute the ""greeks"" using autograd. The loss from ""greeks"" can be added to the price loss function to further improve the learning process.

We will also look at nice interactive plots and tools which will help us better understand the learning process in real time and understand how the models work out-of-sample.

Background Knowledge:

Basic knowledge of financial derivatives especially options.

Bio: 

Chakri Cherukuri is a senior researcher in the Quantitative Research group within the CTO office at Bloomberg LP. His research interests include quantitative portfolio management, algorithmic trading strategies, applied machine learning and numerical methods. Previously, he built analytical tools for the trading desks at Goldman Sachs and Lehman Brothers. Before that he worked in the Silicon Valley for startups building enterprise software systems. He is a core contributor and steering council member of bqplot, a 2D plotting library for the Jupyter notebook. He has extensive experience in numerical computing and software development.
He holds an undergraduate degree in mechanical engineering from Indian Institute of Technology, Madras, and an MS in computational finance from Carnegie Mellon University.