In his talk, Robin will describe the history of passive index investing, right from its origins in the 1960s to the present day and how it has grown to be a significant part of financial markets. The talk will be partially based on Robin’s forthcoming book on passive index investing, which will be published by Penguin/Random House next year.
In this talk, I will outline the design of a distributed options market making system, covering the essential concepts of market making, basic options pricing, particular computational challenges encountered in options market making systems and how to address them using precomputation and approximation based strategies utilizing a parallel, distributed computing architecture.
With applications from biology to finance, data-driven approaches for inferring the behavior of complex, dynamical systems are of wide practical interest. However, modern machine learning requires a near-infinite supply of data to adequately predict these behaviors when the number of system components is large. Instead, this talk introduces the Principle of Maximum Caliber, a generalization of Maximum Entropy to trajectories, as a way to infer dynamical features given limited information.
The focus of this talk is on two recent advances in applying Max Cal to large networks.
We have three short talks which are detailed below.
TITLE: Complex Networks in Finance – Uri Lee
Uri will present the network visualisation tools in the Mlfinlab package and the theory behind why network analysis is important in finance.
TITLE: Synthetic data generation with MlFinLab – David Munoz Constantine
How to use MlFinLab’s synthetic data generation module to augment your models. Why do we need synthetic data when we live in an age of data abundance? What kind of properties synthetic data must have for it to be useful?
TITLE: Statistical Arbitrage with the Ornstein-Uhlenbeck Model – Valeriia Pervushyna
Presentation of OrnsteinUhlenbeck submodule of Mlfinlab package that allows the user both to create an optimal mean-reverting portfolio and to find the optimal timing of trades using the properties of the Ornstein-Uhlenbeck process.
Riskfuel is focused on providing accurate and inexpensive generation of real-time valuations and risk sensitivities for financial instruments. In this talk, Ryan will highlight some of Riskfuel’s recent achievements including the fast and accurate deep neural network (DNN) representation of a high dimensional Bermudan swaption model. He will also discuss some novel techniques recently developed at Riskfuel, including a technique to handle the discontinuities present in the valuation functions of many common financial instruments.