Monte carlo tree search for trading and hedging

Edoardo Vittori, Amarildo Likmeta, Marcello Restelli

Abstract: Monte Carlo Tree Search (MCTS) has had very exciting results in the field of two-player games. In this paper, we analyze the behavior of these algorithms in the financial field, in trading where, to the best of our knowledge, it has never been applied before and in option hedging. In particular, using MCTS algorithms capable of handling stochastic states and continuous actions, we setup a practical framework testing it on real data both in the trading and hedging case.