Sequential decision making is a pervasive and inescapable requirement of every day life. Deciding upon which sequence of actions to take is especially difficult in financial markets which are in a constant state of flux. MDPs and POMDPs provide a powerful framework for many sequential decision making problems in financial markets. We present novel techniques to calculate exact and closed-form solutions to new classes of MDPs and POMDPs by leveraging Symbolic Dynamic Programming (SDP) and applying them to the zero-sum game between a binary option trader and an adversarial market, lgorithmic market making with inventory and sensitivity analysis of an optimal transaction execution model to its parameters.
Shamin Kinathil is a PhD student in Computer Science at ANU and is affiliated with CSIRO/Data61. His research focus is on closed-form solutions to sequential decision making within markets. Prior to studying at ANU, he received an MSc (Statistics) and a BE (Bioinformatics)/BSc (Biotechnology) at the University of New South Wales.