|
Learning exercise policies for american options
Y Li, Csaba Szepesvari and D Schuurmans
In: AISTAT-09, 16-18 Apr 2009, Clearwater Beach, Florida, USA.
AbstractOptions are important instruments in modern
nance. In this paper, we investigate
reinforcement learning (RL) methods|
in particular, least-squares policy iteration
(LSPI)|for the problem of learning exercise
policies for American options. We develop
nite-time bounds on the performance of the
policy obtained with LSPI and compare LSPI
and the tted Q-iteration algorithm (FQI)
with the Longsta-Schwartz method (LSM),
the standard least-squares Monte Carlo algorithm
from the nance community. Our empirical
results show that the exercise policies
discovered by LSPI and FQI gain larger payo
s than those discovered by LSM, on both
real and synthetic data. Furthermore, we
nd that for all methods the policies learned
from real data generally gain similar payo
s to the policies learned from simulated
data. Our work shows that solution methods
developed in machine learning can advance
the state-of-the-art in an important and challenging
application area, while demonstrating
that computational nance remains a
promising area for future applications of machine
learning methods. [Edit]
|
