Stock Selection : An Innovative Application of Genetic
Programming Methodology
Y. Becker, P. Fei, and A. Lester. Genetic Programming Theory and Practice IV, volume 5 of Genetic and Evolutionary Computation, chapter 12, Springer, Ann Arbor, (11-13 May 2006)
Abstract
One of the major challenges in an information-rich
financial market is how effectively to derive an
optimum investment solution among vast amounts of
available information. The most efficacious combination
of factors or information signals can be found by
evaluating millions of possibilities, which is a task
well beyond the scope of manual efforts. Given the
limitations of the manual approach, factor combinations
are typically linear. However, the linear combination
of factors might be too simple to reflect market
complexities and thus fully capture the predictive
power of the factors. A genetic programming process can
easily explore both linear and non-linear formulae. In
addition, the ease of evaluation facilitates the
consideration of broader factor candidates for a stock
selection model. Based upon SSgA's previous research on
using genetic programming techniques to develop
quantitative investment strategies, we extend our
application to develop stock selection models in a
large investable stock universe, the S&P 500 index. Two
different fitness functions are designed to derive GP
models that accommodate different investment
objectives. First, we demonstrate that the GP process
can generate a stock selection model for an low active
risk investment style. Compared to a traditional model,
the GP model has significantly enhanced future stock
return ranking capability. Second, to suit an active
investment style, we also use the GP process to
generate a model that identifies the stocks with future
returns lying in the fat tails of the return
distribution. A portfolio constructed based on this
model aims to aggressively generate the highest returns
possible compared to an index following portfolio. Our
tests show that the stock selection power of the GP
models is statistically significant. Historical
backtest results indicate that portfolios based on GP
models outperform the benchmark and the portfolio based
on the traditional model. Further, we demonstrate that
GP models are more robust in accommodating various
market regimes and have more consistent performance
than the traditional model.
part of Riolo:2006:GPTP Published Jan 2007
after the workshop
Principal, Head of US Active Equity Research, Advanced
Research Center, State Street Global Advisors, Boston,
MA 02111;
%0 Book Section
%1 Becker:2006:GPTP
%A Becker, Ying
%A Fei, Peng
%A Lester, Anna M.
%B Genetic Programming Theory and Practice IV
%C Ann Arbor
%D 2006
%E Riolo, Rick L.
%E Soule, Terence
%E Worzel, Bill
%I Springer
%K 500, Arbitrage Asset Capital Information Model, Pricing Quantitative S&P Stock Technical algorithms, asset coefficient, equity genetic management market, models, programming, quantitative ratio, rules, selection selection, stock trading
%P -
%T Stock Selection : An Innovative Application of Genetic
Programming Methodology
%V 5
%X One of the major challenges in an information-rich
financial market is how effectively to derive an
optimum investment solution among vast amounts of
available information. The most efficacious combination
of factors or information signals can be found by
evaluating millions of possibilities, which is a task
well beyond the scope of manual efforts. Given the
limitations of the manual approach, factor combinations
are typically linear. However, the linear combination
of factors might be too simple to reflect market
complexities and thus fully capture the predictive
power of the factors. A genetic programming process can
easily explore both linear and non-linear formulae. In
addition, the ease of evaluation facilitates the
consideration of broader factor candidates for a stock
selection model. Based upon SSgA's previous research on
using genetic programming techniques to develop
quantitative investment strategies, we extend our
application to develop stock selection models in a
large investable stock universe, the S&P 500 index. Two
different fitness functions are designed to derive GP
models that accommodate different investment
objectives. First, we demonstrate that the GP process
can generate a stock selection model for an low active
risk investment style. Compared to a traditional model,
the GP model has significantly enhanced future stock
return ranking capability. Second, to suit an active
investment style, we also use the GP process to
generate a model that identifies the stocks with future
returns lying in the fat tails of the return
distribution. A portfolio constructed based on this
model aims to aggressively generate the highest returns
possible compared to an index following portfolio. Our
tests show that the stock selection power of the GP
models is statistically significant. Historical
backtest results indicate that portfolios based on GP
models outperform the benchmark and the portfolio based
on the traditional model. Further, we demonstrate that
GP models are more robust in accommodating various
market regimes and have more consistent performance
than the traditional model.
%& 12
%@ 0-387-33375-4
@incollection{Becker:2006:GPTP,
abstract = {One of the major challenges in an information-rich
financial market is how effectively to derive an
optimum investment solution among vast amounts of
available information. The most efficacious combination
of factors or information signals can be found by
evaluating millions of possibilities, which is a task
well beyond the scope of manual efforts. Given the
limitations of the manual approach, factor combinations
are typically linear. However, the linear combination
of factors might be too simple to reflect market
complexities and thus fully capture the predictive
power of the factors. A genetic programming process can
easily explore both linear and non-linear formulae. In
addition, the ease of evaluation facilitates the
consideration of broader factor candidates for a stock
selection model. Based upon SSgA's previous research on
using genetic programming techniques to develop
quantitative investment strategies, we extend our
application to develop stock selection models in a
large investable stock universe, the S&P 500 index. Two
different fitness functions are designed to derive GP
models that accommodate different investment
objectives. First, we demonstrate that the GP process
can generate a stock selection model for an low active
risk investment style. Compared to a traditional model,
the GP model has significantly enhanced future stock
return ranking capability. Second, to suit an active
investment style, we also use the GP process to
generate a model that identifies the stocks with future
returns lying in the fat tails of the return
distribution. A portfolio constructed based on this
model aims to aggressively generate the highest returns
possible compared to an index following portfolio. Our
tests show that the stock selection power of the GP
models is statistically significant. Historical
backtest results indicate that portfolios based on GP
models outperform the benchmark and the portfolio based
on the traditional model. Further, we demonstrate that
GP models are more robust in accommodating various
market regimes and have more consistent performance
than the traditional model.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Ann Arbor},
author = {Becker, Ying and Fei, Peng and Lester, Anna M.},
biburl = {https://www.bibsonomy.org/bibtex/29fec610cd789f915c6108d441426c7f4/brazovayeye},
booktitle = {Genetic Programming Theory and Practice {IV}},
chapter = 12,
editor = {Riolo, Rick L. and Soule, Terence and Worzel, Bill},
interhash = {82e8ed1cff1abf6412b49c1b8195088f},
intrahash = {9fec610cd789f915c6108d441426c7f4},
isbn = {0-387-33375-4},
keywords = {500, Arbitrage Asset Capital Information Model, Pricing Quantitative S&P Stock Technical algorithms, asset coefficient, equity genetic management market, models, programming, quantitative ratio, rules, selection selection, stock trading},
month = {11-13 May},
notes = {part of \cite{Riolo:2006:GPTP} Published Jan 2007
after the workshop
Principal, Head of US Active Equity Research, Advanced
Research Center, State Street Global Advisors, Boston,
MA 02111;},
pages = {-},
publisher = {Springer},
series = {Genetic and Evolutionary Computation},
size = {16 pages},
timestamp = {2008-06-19T17:36:23.000+0200},
title = {Stock Selection : An Innovative Application of Genetic
Programming Methodology},
volume = 5,
year = 2006
}