傳統的投資組合保險 (portfolio insurance; PI) 策略，例如 constant proportion portfolio insurance (CPPI) 策略，只有考慮保本限制而並未考慮目標因素。然而研究顯示出兩種相互矛盾的投資者風險態度，分別是低財富風險趨避以及高財富風險趨避。雖然低財富風險趨避可以由CPPI策略來解釋，但是高財富風險趨避無法由CPPI策略來解釋。我們認為這些矛盾現象可以經由投資組合保險觀點與目標導向觀點來解釋。本研究提出了一個目標導向 (goal-directed ; GD) 策略來顯示投資者的目標導向投資行為。本研究更進一步的結合與保本無關的GD策略以及與保目標無關的CPPI策略，以建立一個分段線性目標導向CPPI (GDCPPI) 策略。分段線性GDCPPI策略中存在一個經由GD策略與CPPI策略相交的財富水準M值。此一M值能引導投資者當目前的財富低於該M值時應採用CPPI策略，當目前的財富高於該M值時應採用GD策略。
更進一步的，我們擴充分段線性GDCPPI策略成為分段非線性GDCPPI策略。我們也應用time invariant portfolio protection (TIPP) 的允許動態保本底限與目標上限的觀念來取代CPPI的靜態觀念，而將分段GDCPPI策略擴充成分段GDTIPP策略。因此分段GDCPPI策略與分段GDTIPP策略都是分段GDPI策略的兩個特例。當建立分段非線性GDPI策略時，採用明確的M值是不合理的，因為投資者會遭遇到無法事先決定由非線性PI策略與非線性GD策略來產生M值的困難。因此我們採用最小值函數來順利解決此一問題。亦即分段非線性GDPI策略等於非線性PI策略與非線性GD策略的其中一個最小的值。應用此一最小值函數會讓分段非線性GDPI策略仍然保有M值的觀念，但卻是以隱性的方式來操作。同時分段線性GDPI策略亦可以採用此以最小值函數來獲得相同的效果，並建立一個隱性分段線性GDPI策略。
本研究進行了許多的實驗以辯證我們所提的兩個命題：存在分段非線性GDPI策略優於分段線性GDPI策略，以及存在其他資料驅動 (data-driven) 的技術以便於找到比透過Brownian技術所產生的更好的分段線性GDPI策略。本研究採用了遺傳演算法(GA)來找出更好的分段線性GDPI策略。同時本研究調適了傳統的遺傳程式規劃(GP)成為森林式GP，以建立分段非線性GDPI策略。統計檢定結果顯示，由GP所產生的交易策略優於由GA所產生的交易策略，同時由GA所產生的交易策略優於由Brownian技術所產生的交易策略。因此檢定結果能辯證我們所提出的命題。

Traditional portfolio insurance (PI) strategy such as constant
proportion portfolio insurance (CPPI) only considers the floor
constraint but not the goal aspect.
There seems to be two contradictory risk-attitudes
according to different studies: low wealth risk aversion and high
wealth risk aversion. Although low wealth risk aversion can be
explained by the CPPI strategy, high wealth risk aversion can not be
explained by CPPI. We argue that these contradictions can be
explained from two perspectives: the portfolio insurance perspective
and the goal-directed perspective.
This study proposes a goal-directed (GD) strategy to express an
investor''s goal-directed trading behavior and combines this
floor-less GD strategy with the goal-less CPPI strategy to form a
piecewise linear goal-directed CPPI (GDCPPI) strategy.
The piecewise linear GDCPPI strategy shows that there is a wealth
position M at the intersection of the GD strategy and CPPI strategy. This
M position guides investors to apply CPPI strategy or GD strategy
depending on whether the current wealth is less than or greater than
M respectively.
In addition, we extend the piecewise linear GDCPPI strategy to a
piecewise nonlinear GDCPPI strategy. Moreover, we extend the piecewise
GDCPPI strategy to the piecewise GDTIPP strategy by applying the
time invariant portfolio protection (TIPP) idea,
which allows variable floor and goal comparing to the
constant floor and goal for piecewise GDCPPI strategy. Therefore, piecewise
GDCPPI strategy and piecewise GDTIPP strategy are two special
cases of piecewise goal-directed portfolio insurance (GDPI) strategies.
When building the piecewise nonlinear GDPI strategies,
it is difficult to preassign an explicit $M$ value when
the structures of nonlinear PI strategies and nonlinear GD strategies
are uncertain.
To solve this problem, we then apply the minimum function
to build the piecewise nonlinear GDPI strategies,
which these strategies still apply the $M$ concept
but operate it in an implicit way.
Also, the piecewise linear GDPI strategies can attain the same effect
by applying the minimum function to form implicit piecewise linear GDPI strategies.
This study performs some experiments to justify our
propositions for piecewise GDPI strategies: there are nonlinear GDPI strategies
that can outperform the linear GDPI strategies and
there are some data-driven techniques
that can find better linear GDPI strategies than the solutions
found by Brownian technique.
The GA and forest genetic programming (GP) are two data-drive
techniques applied in this study.
This study applies genetic algorithm (GA) technique to find better
piecewise linear GDPI strategy parameters than those under
Brownian motion assumption.
This study adapts traditional GP to a forest GP in order to
generate piecewise nonlinear GDPI strategies. The statistical
tests show that the GP strategy outperforms the GA strategy which in
turn outperforms the Brownian strategy. These statistical tests therefore
justify our propositions.

[1] M. Andrew and R. Prager. Genetic programming for the acquistion of dou-
ble auction market strategies. In K. KinnearJr, editor, Advances in genetic
programming, pages 355{368. The MIT Press, Cambridge, MA, 1994.
[2] T. BÄack, D. B. Fogel, and T. Michalewicz, editors. Evolutionary Computation
1: Basic Algorithms and Operators. IOP, 2000.
[3] T. BÄack, D. B. Fogel, and T. Michalewicz, editors. Evolutionary Computation
2: Advanced Algorithms and Operators. IOP, 2000.
[4] R. J. Jr. Bauer. Genetic Algorithms and Investment Strategies. John Wiley
& Sons, New York, 1994.
[5] D. Beasley. Posible applications of evolutionary computation. In T. BÄack,
D. B. Fogel, and T. Michalewicz, editors, Evolutionary Computation 1: Basic
Algorithms and Operators, pages 4{19. IOP, 2000.
[6] L. Beltrametti, R. Fiorentini, L. Marengo, and R. Tamborini. A learning-to-
forecast experiment on the foreign exchange market with a classi¯er system.
Journal of Economic Dynamics and Control, 21:1543{1575, 1997.
[7] S. Bhattachary, O. Pietet, and G. Zumbach. Representational semantics
for genetic programming based learning in high-frequency ¯nancial data. In
J. Koza, W. Banzhaf, K. Chellapilla, K. Beb, M. Dorigo, D. Fogel, M. Gar-
zon, H. Iba, and R. Riolo, editors, Genetic Programming 1998: Proceedings of
the third annual conference, pages 11{16, San Francisco, CA, 1998. Morgan
Kaufmann.
[8] F. Black and R. Jones. Simplifying portfolio insurance. Journal of Portfolio
Management, 14(1):48{51, Fall 1987.
[9] F. Black and A. F. Perold. Theory of constant proportion portfolio insurance.
Journal of Economic Dynamics and Control, 16:403{426, 1992.
[10] F. Black and M. Scholes. The pricing of options and corporate liabilities.
Journal of Political Economy, 81(3):637{659, 1973.
[11] Zvi Bodie, Alex Kane, and Alan J. Marcus. Investments. Irwin/McGraw-Hill,
4th edition, 1999.
[12] K. Brown, W. Harlow, and L. Starks. Of tournaments and temptations: An
analysis of managerial incentives in mutual fund industry. Journal of Finance,
51:85{110, 1996.
[13] Sid Browne. Survival and growth with a liability: Optimal portfolio strategies
in continuous time. Mathematics of Operations Research, 22(2):468{493, 1997.
[14] J. A. Busse. Another look at mutual fund tournaments. Journal of Financial
and Quantitative Analysis, 36(1):53{73, March 2001.
[15] C. Caldwell and V. S. Johnston. Tracking a criminal suspect through face-
space" with a genetic algorithm. In Proceedings of the Fourth International
Conference on Genetic Algorithms, pages 416{421, 1991.
[16] A. Chatterjee and P. Siarry. Nonlinear inertia weight variation for dynamic
adaptation in particle swarm optimization. Computers & Operations Re-
search, 33(3):859{871, 2006.
[17] A. P. Chen and M. Y. Chen. Integrating extended classi¯er system and knowl-
edge extraction model for ¯nancial investment prediction: An empirical study.
Expert Systems with Applications, 31(1):174{183, 2006.
[18] J. S. Chen. Trading strategy generation using genetic algorithms. Asian
Journal of Information Technology, 4(4), 2005.
[19] J. S. Chen and B. P. Y. Liao. Goal-directed portfolio insurance. In K. Chen
L. Wang and Y. S. Ong, editors, ICNC 2005, LNCS 3612, pages 798{807,
Heidelberg:Berlin, Springer-Verlag, 2005.
[20] J. S. Chen and P. C. Lin. Multi-valued stock valuation based on fuzzy ge-
netic programming approach. In Proceedings of the 7th Joint Conference on
Information Sciences (The Third International Workshop on Computational
Intelligence in Economics and Finance), pages 1124{1127, Cary, North Car-
olina, September 2003.
[21] J. S. Chen, P. C. Wu, and P. Y. Liao. Neural network forecasting of TAIMEX
index futures. In Proceedings of the Second Asia-Paci¯c Conference on Ge-
netic Algorithms and Applications, pages 403{408, Hong Kong, 2000. Global-
Link Publishing Company.
[22] S. Chen, C. Yeh, and W. Lee. Option pricing with genetic programming. In
J. Koza, W. Banzhaf, K. Chellapilla, K. Beb, M. Dorigo, D. Fogel, M. Garzon,
H. Iba, and R. Riolo, editors, Genetic Programming 1998: Proceedings of the
Third Annual Conference, pages 32{37, San Francisco, CA, 1998. Morgan
Kaufmann.
[23] S. H. Chen. Genetic programming, predictability, and stock market e±ciency.
In L. Vlacic, T. Nguyen, and D. Cecez-Kecmanovic, editors, Modelling and
control of national and regional economies, pages 283{288. Pergamon Press,
Oxford, Great Britain, 1996.
[24] S. H. Chen. Hedging derivative securities with genetic programming. In
Application of machine learning and data mining in ¯nance: Workshop at
ECMI-98. Dorint-Parkhotel, Chemnitz, Germany, 24 April 1998. ECML-98
Workshop 6.
[25] S. H. Chen and C. H. Yeh. Predicting stock returns with genetic program-
ming: Do the short-term nonlinear regularities exist? In D. Fisher, editor,
Proceedings of the Fifth International Workshop on Arti¯cial Intelligence and
Statistics, pages 95{101, F. Lauderdale, Florida, 1995.
[26] S. H. Chen and C. H. Yeh. Using genetic programming to model volatility
in ¯nancial time series. In J. Koza, J. Deb, M. Dorigo, D. Fogel, M. Garzon,
H. Iba, and R. Riolo, editors, Genetic Programming 1997: Proceedings of
the Second Annual Conference, pages 58{63, Stanford University, CA, 1996.
Morgan Kaufmann.
[27] S. H. Chen and C. H. Yeh. Toward a computable approach to the e±cient
market hypothesis: An application of genetic programming. Journal of Eco-
nomic Dynamics and Control, 21:1043{1063, 1997.
[28] J. Chevalier and G. Ellison. Risk taking by mutual funds as a response to
incentives. Journal of Political Economy, 105:1167{1200, 1997.
[29] N. Chidambaran, J. Trigueros, and C. Lee. Option pricing via genetic pro-
gramming. In S. H. Chen, editor, Evolutionary Computation in Economics
and Finance, pages 383{397, Heidelberg, New York, 2002. Physica-Verlag.
[30] C. A. Coello. An updated survey of GA-based multiobjective op-
timization techniques. ACM Computing Survey, 32(2):109{143, 2000.
http://doi.acm.org/10.1145/358923.358929.
[31] A. M. Colin. Genetic algorithms for ¯nancial modeling. In G. J. Deboeck,
editor, Trading on the Edge: Neural, Genetic and Fuzzy Systems for Chaotic
Financial Markets, pages 148{173. Wiley, 1994.
[32] A. Colorni, M. Dorigo, and V. Maniezzo. Distributed optimization by ant
colonies. In Proceedings of ECAL91{European Conference on Arti¯cial Life,
pages 134{142, Paris, France: Elsevier Publishing, 1998.
[33] G. J. Deboeck, editor. Trading on the Edge: Neural, Genetic and Fuzzy
Systems for Chaotic Financial Markets. John Wiley & Sons, New York, 1994.
[34] G. J. Deboeck. Using GAs to optimize a trading system. In G. J. Deboeck,
editor, Trading on the Edge: Neural, Genetic and Fuzzy Systems for Chaotic
Financial Markets, pages 174{188. Wiley, 1994.
[35] M. A. H. Dempster and V. Leemans. An automated FX trading system using
adaptive reinforcement learning. Expert Systems with Applications, 30(3):543{
552, 2006.
[36] M. Dorigo, E. Bonabeau, and G. Theraulaz. Ant algorithms and stigmergy.
Future Generation Computer Systems, 16:851{871, 2000.
[37] R. C. Eberhart and J. Kennedy. Anewoptimiser using particle swarm theory.
In Proceedings of the Sixth International Symposium on Micro Machine and
Human Science, pages 39{43. IEEE Service Center, 1995.
[38] J. T. Eglit. Trend prediction in ¯nancial time series. In J. Koza, editor,
Genetic algorithms at Stanford, pages 31{40. Stanford Bookstore, Stanford,
CA, 1994.
[39] T. Estep and M. Kritzman. TIPP: Insurance without complexity. Journal of
Portfolio Management, 14:38{42, 1988.
[40] D. E. Goldberg. Genetic Algorithm in Search, Optimization and Machine
Learning. Addison-Wesley, 1989.
[41] S. J. Grossman and Z. Zhou. Optimal investment strategies for controlling
drawdowns. Mathematical Finance, 3(3):241{276, 1993.
[42] J. W. Hall. Adaptive selection of U.S. stocks with neural nets. In G. J.
Deboeck, editor, Trading on the Edge: Neural, Genetic and Fuzzy Systems
for Chaotic Financial Markets, pages 45{65. Wiley, 1994.
[43] J. H. Holland. Adaptation in Natural and Arti¯cial Systems: An Introductory
Analysis with Applications to Biology, Control, and Arti¯cial Intelligence.
MIT Press, 1st MIT Press edition, 1992. University of Michigan Press, 1st
edition, 1975.
[44] J. H. Holland and J. S. Reitman. Cognitive systems based on adaptive al-
gorithms. In D. A. Waterman and F. Hayes-Roth, editors, Pattern-Directed
Inference Systems, pages 313{329. Academic Press, New York, 1978.
[45] H. Hsu, E. Ho, and J. Chuang. The path dependence of alternative portfo-
lio insurance strategies. Commerce & Management Quarterly, 5(4):435{455,
2004.
[46] J. C. Jackwerth. Recovering risk aversion from option prices and realized
returns. The Review of Financial Studies, 13(2):433{451, 2000.
[47] G. S. Jang and F. Lai. Intelligent trading of an emerging market. In G. J.
Deboeck, editor, Trading on the Edge: Neural, Genetic, and Fuzzy Systems
for Chaotic Financial Markets, chapter 5, pages 80{101. John Wiley & Sons,
1994.
[48] M. Kaboudan. Forecasting stock returns using genetic programming in C++.
In D. Cook, editor, FLAIRS Proceedings of the Eleventh International Florida
Arti¯cial Intelligence Research Symposium Conference, pages 73{77, Menlo
Park, CA, 1998. AAAI Press.
[49] M. Kaboudan. GP forecasts of stock prices for pro¯table trading. In S.H.
Chen, editor, Evolutionary Computation in Economics and Finance, pages
359{381. Physica-Verlag, Heidelberg, New York, 2002.
[50] K. Kamijo and T. Tanigawa. Stock price pattern recognition: A recurrent
neural network approach. In Proceedings of the 1990 International Joint Con-
ference on Neural Networks, pages 215{221, 1990.
[51] C. Keber. Evoluationary computation in option pricing: Determining implied
volatilities based on American put options. In S. H. Chen, editor, Evolutionary
Computation in Economics and Finance, pages 399{415, Heidelberg, New
York, 2002. Physica-Verlag.
[52] K. J. Kim. Arti¯cial neural networks with evolutionary instance selection for
¯nancial forecasting. Expert Systems with Applications, 30(3):519{526, 2006.
[53] M. J. Kim, S. H. Min, and I. Han. An evolutionary approach to the combina-
tion of multiple classi¯ers to predict a stock price index. Expert Systems with
Applications, 31(2):241{247, 2006.
[54] T. Kimoto, K. Asakawa, M. Yoda, and M. Takeoka. Stock market prediction
system with modular neural networks. In Proceedings of the 1990 Interna-
tional Joint Conference on Neural Networks, pages 1{6, 1990.
[55] J. R. Koza. Genetic Programming: On the Programming of Computers by
Means of Natural Selection. MIT Press, Massachusetts, 1992.
[56] J. R. Koza. Introduction to genetic programming. In K. Jr Kinnear, editor,
Advances in genetic programming, pages 21{42. The MIT Press, Cambridge,
MA, 1994.
[57] P. Y. Liao and J. S. Chen. Dynamic trading strategy learning model using
learning classi¯er systems. In Proceedings of the 2001 IEEE Congress on
Evolutionary Computation, pages 783{789, Seoul, Korea, 2001.
[58] A. W. Lo and A. C. MacKinlay. A non-random walk down wall street. Prince-
ton University Press, Princeton, NJ, 1999.
[59] Harry Markowitz. Portfolio selection. Journal of Finance, 7:77{91, 1952.
[60] M. Mitchell. An Introduction to Genetic Algorithms. MIT Press, 1996.
[61] J. J. Murphy. Technical Analysis of the Futures Markets. New York Institute
of Finance, 1999.
[62] K. J. Oh, T. Y. Kim, S. H. Min, and H. Y. Lee. Portfolio algorithm based
on portfolio beta using genetic algorithm. Expert Systems with Applications,
30(3):527{534, 2006.
[63] C. S. Ong, J. J. Huang, and G.H. Tzeng. Building credit scoring models using
genetic programming. Expert Systems with Applications, 29(1):41{47, 2005.
[64] M. Oussaidene, B. Chopard, O. Pictet, and M. Tomassini. Parallel genetic pro-
gramming: An application to trading models evolution. In J. Koza, D. Gold-
berg, D. Fogel, and R. Riolo, editors, Genetic Programming 1996: Proceedings
of the First Annual Conference, pages 357{362, Cambridge, MA, 1996. The
MIT Press.
[65] A. F. Perold and W. F. Sharpe. Dynamic strategies for asset allocation.
Financial Analyst Journal, Jan/Feb:16{27, 1988.
[66] K. B. Pratt and E. Fink. Search for patterns in compressed times series.
International Journal of Image and Graphics, 2(1):89{102, 2002.
[67] M. Rubinstein and H. E. Leland. Replacing options with positions in stock
and cash. Financial Analysts Journal, 37(4):63{72, 1981.
[68] J. Sarma and K. De Jong. Generation gap methods. In T. BÄack, D. B. Fogel,
and T. Michalewicz, editors, Evolutionary Computation 1: Basic Algorithms
and Operators, pages 205{227. Institute of Physics Publishing, Bristol, 2000.
[69] William F. Sharpe. A simpli¯ed model for portfolio analysis. Management
Science, 9:277{293, 1963.
[70] J. C. P. Shieh. Fundamentals of Investment. BestWise, Taipei, 2003.
[71] R. E. Smith. A report on the ¯rst international workshop on learning classi¯er
systems. In Proceedings of the First International Workshop on Learning
Classi¯er Systems, NASA Johnson Space Center, ftp://lumpi.informatik.uni-
dortmund.de/pub/LCS/papers/lcs92.ps.gz, 1992.
[72] M. Srinivas and L.M. Patnaik. Genetic algorithms: A survey. Computer,
27(6):17{26, 1994.
[73] A. Stafylopatis and K. Blekas. Autonomous vehicle navigation using evolu-
tionary reinforcement learning. European Journal of Operational Research,
108:306{318, 1998.
[74] T. Tanigawa and K. Kamijo. Stock price pattern matching system: Dynamic
programming neural networks approach. In Proceedings of the 1992 Interna-
tional Joint Conference on Neural Networks, pages 465{471, 1992.
[75] J. Tayler. Risk-taking behavior in mutual fund tournaments. Journal of
Economic Behavior & Organization, 50:373{383, 2003.
[76] A. Tsakonas, G. Dounias, M. Doumpos, and C. Zopounidis. Arti¯cial neural
networks with evolutionary instance selection for ¯nancial forecasting. Expert
Systems with Applications, 30(3):449{461, 2006.
[77] M. A. Warren. Stock price prediction using genetic programming. In J. Koza,
editor, Genetic algorithms at Stanford, pages 180{184. Stanford Bookstore,
Stanford, CA, 1994.
[78] S. W. Wilson. Classi¯er ¯tness based on accuracy. Evolutionary Computation,
3(2):149{175, 1995.
[79] S. W. Wilson and D. E. Goldberg. A critical review of classi¯er systems.
In J. D. Scha®er, editor, Proceedings of the Third International Conference
on Genetic Algorithms, pages 244{255, San Mateo, California, 1989. Morgan
Kaufmann Publishers.
[80] M. Yoda. Predicting the tokyo stock market. In G. J. Deboeck, editor, Trading
on the Edge, chapter 4, pages 66{79. John Wiely & Sons, Inc., 1994.