An analysis of a hybrid neural network and pattern recognition technique for predicting short-term increases in the NYSE composite index

被引：34

作者：

Leigh, W ^{[1
]}

Paz, M

Purvis, R

机构：

[1] Univ Cent Florida, Coll Business, Dept Management Informat Syst, Orlando, FL 32816 USA

[2] Univ Louisville, Dept Civil Engn, Speed Sch Sci, Louisville, KY USA

[3] Clemson Univ, Dept Management, Clemson, SC 29634 USA

来源：

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE | 2002年 / 30卷 / 02期

关键词：

stock market forecasting; neural networks; pattern recognition; heuristics; financial decision support; efficient markets hypothesis; technical analysis;

D O I：

10.1016/S0305-0483(01)00057-3

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

We introduce a method for combining template matching, from pattern recognition, and the feed-forward neural network, from artificial intelligence, to forecast stock market activity. We evaluate the effectiveness of the method for forecasting increases in the New York Stock Exchange Composite Index at a 5 trading day horizon. Results indicate that the technique is capable of returning results that are superior to those attained by random choice. (C) 2002 Elsevier Science Ltd. All rights reserved.

引用

页码：69 / 76

页数：8

共 18 条

[1]

Downes J., 2014, DICT FINANCE INVESTM

[2] DECISION-SUPPORT IN NONCONSERVATIVE DOMAINS - GENERALIZATION WITH NEURAL NETWORKS [J].

DUTTA, S ;

SHEKHAR, S ;

WONG, WY .

DECISION SUPPORT SYSTEMS, 1994, 11 (05) :527-544

[3]

EDWARDS RD, 1997, TECHNICAL ANAL STOCK

[4] EFFICIENT CAPITAL-MARKETS .2. [J].

FAMA, EF .

JOURNAL OF FINANCE, 1991, 46 (05) :1575-1617

[5]

Hart P.E., 1973, Pattern recognition and scene analysis

[6]

Haugen R.A., 1997, Modern Investment Theory

[7] Neural network models for time series forecasts [J].

Hill, T ;

OConnor, M ;

Remus, W .

MANAGEMENT SCIENCE, 1996, 42 (07) :1082-1092

[8]

Hoptroff R. G., 1993, NEURAL COMPUT APPL, V1, P59, DOI DOI 10.1007/BF01411375

[9]

Kennedy RL., 1997, SOLVING DATA MINING

[10] Graded forecasting using an array of bipolar predictions: application of probabilistic neural networks to a stock market index [J].

Kim, SH ;

Chun, SH .

INTERNATIONAL JOURNAL OF FORECASTING, 1998, 14 (03) :323-337

← 1 2 →