A fusion model of HMM, ANN and GA for stock market forecasting

被引：193

作者：

Hassan, Md. Rafiul ^{[1
]}

Nath, Baikunth ^{[1
]}

Kirley, Michael ^{[1
]}

机构：

[1] Univ Melbourne, Dept Comp Sci & Software Engn, Carlton, Vic 3010, Australia

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2007年 / 33卷 / 01期

关键词：

forecasting; stock market; Hidden Markov Model; Artificial Neural Network; Genetic Algorithm; ARTIFICIAL NEURAL-NETWORKS; OPTIMIZATION;

D O I：

10.1016/j.eswa.2006.04.007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we propose and implement a fusion model by combining the Hidden Markov Model (HMM), Artificial Neural Networks (ANN) and Genetic Algorithms (GA) to forecast financial market behaviour. The developed tool can be used for in depth analysis of the stock market. Using ANN, the daily stock prices are transformed to independent sets of values that become input to HMM. We draw on GA to optimize the initial parameters of HMM. The trained HMM is used to identify and locate similar patterns in the historical data. The price differences between the matched days and the respective next day are calculated. Finally, a weighted average of the price differences of similar patterns is obtained to prepare a forecast for the required next day. Forecasts are obtained for a number of securities in the IT sector and are compared with a conventional forecast method. (c) 2006 Elsevier Ltd. All rights reserved.

引用

页码：171 / 180

页数：10

共 34 条

[1]

Abraham A, 2001, LECT NOTES COMPUT SC, V2074, P337

[2]

[Anonymous], P INT JOINT C NEUR N

[3] GLOBAL OPTIMIZATION OF A NEURAL NETWORK-HIDDEN MARKOV MODEL HYBRID [J].

BENGIO, Y ;

DEMORI, R ;

FLAMMIA, G ;

KOMPE, R .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02) :252-259

[4]

Box GEP, 1976, Time Series Analysis: Forecasting and Control, V2nd

[5]

Chau CW, 1997, INT CONF ACOUST SPEE, P1727, DOI 10.1109/ICASSP.1997.598857

[6] NEURAL NETWORKS - A REVIEW FROM A STATISTICAL PERSPECTIVE [J].

CHENG, B ;

TITTERINGTON, DM .

STATISTICAL SCIENCE, 1994, 9 (01) :2-30

[7] Use of runs statistics for pattern recognition in genomic DNA sequences [J].

Cheung, LWK .

JOURNAL OF COMPUTATIONAL BIOLOGY, 2004, 11 (01) :107-124

[8] A neural network approach to mutual fund net asset value forecasting [J].

Chiang, WC ;

Urban, TL ;

Baldridge, GW .

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 1996, 24 (02) :205-215

[9]

Choi J., 1995, Proceedings of the third annual international conference on artificial intelligence applications on wall street, P63

[10] AN APPROACH TO CARDIAC-ARRHYTHMIA ANALYSIS USING HIDDEN MARKOV-MODELS [J].

COAST, DA ;

STERN, RM ;

CANO, GG ;

BRILLER, SA .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1990, 37 (09) :826-836

← 1 2 3 4 →