Predicting mutual fund performance using artificial neural networks

Daniel C. Indro, C. X. Jiang, B. E. Patuwo, G. P. Zhang

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

This study utilizes an artificial neural network (ANN) approach to predict the performance of equity mutual funds that follow value, blend and growth investment styles. Using a multi-layer perceptron model and GRG2 nonlinear optimizer, fund-specific historical operating characteristics were used to forecast mutual funds' risk-adjusted return. Results show that ANN generates better forecasting results than linear models for funds of all styles. In addition, our model outperforms that of Chiang et al. [Chiang WC, Urban TL, Baldridge GW. A neural network approach to mutual fund net asset value forecasting. Omega Int J Manage Sci 1996:24;205-215.] in predicting the performance of growth funds. We also employed a heuristic approach of variable selection via neural networks and compared it with the stepwise selection method of linear regression. Results are encouraging in that the reduced ANN models still outperform the linear models for growth and blend funds and yield similar results for value funds.

Original languageEnglish (US)
Pages (from-to)373-380
Number of pages8
JournalOmega
Volume27
Issue number3
DOIs
StatePublished - Jun 1 1999

Fingerprint

Mutual fund performance
Artificial neural network
Mutual funds
Blends
Neural networks
Equity
Heuristics
Investment style
Network model
Asset value
Variable selection
Linear regression
Risk-adjusted returns

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research
  • Information Systems and Management

Cite this

Indro, Daniel C. ; Jiang, C. X. ; Patuwo, B. E. ; Zhang, G. P. / Predicting mutual fund performance using artificial neural networks. In: Omega. 1999 ; Vol. 27, No. 3. pp. 373-380.
@article{9bd699d42a27483091ee359718cab09b,
title = "Predicting mutual fund performance using artificial neural networks",
abstract = "This study utilizes an artificial neural network (ANN) approach to predict the performance of equity mutual funds that follow value, blend and growth investment styles. Using a multi-layer perceptron model and GRG2 nonlinear optimizer, fund-specific historical operating characteristics were used to forecast mutual funds' risk-adjusted return. Results show that ANN generates better forecasting results than linear models for funds of all styles. In addition, our model outperforms that of Chiang et al. [Chiang WC, Urban TL, Baldridge GW. A neural network approach to mutual fund net asset value forecasting. Omega Int J Manage Sci 1996:24;205-215.] in predicting the performance of growth funds. We also employed a heuristic approach of variable selection via neural networks and compared it with the stepwise selection method of linear regression. Results are encouraging in that the reduced ANN models still outperform the linear models for growth and blend funds and yield similar results for value funds.",
author = "Indro, {Daniel C.} and Jiang, {C. X.} and Patuwo, {B. E.} and Zhang, {G. P.}",
year = "1999",
month = "6",
day = "1",
doi = "10.1016/S0305-0483(98)00048-6",
language = "English (US)",
volume = "27",
pages = "373--380",
journal = "Omega",
issn = "0305-0483",
publisher = "Elsevier BV",
number = "3",

}

Predicting mutual fund performance using artificial neural networks. / Indro, Daniel C.; Jiang, C. X.; Patuwo, B. E.; Zhang, G. P.

In: Omega, Vol. 27, No. 3, 01.06.1999, p. 373-380.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting mutual fund performance using artificial neural networks

AU - Indro, Daniel C.

AU - Jiang, C. X.

AU - Patuwo, B. E.

AU - Zhang, G. P.

PY - 1999/6/1

Y1 - 1999/6/1

N2 - This study utilizes an artificial neural network (ANN) approach to predict the performance of equity mutual funds that follow value, blend and growth investment styles. Using a multi-layer perceptron model and GRG2 nonlinear optimizer, fund-specific historical operating characteristics were used to forecast mutual funds' risk-adjusted return. Results show that ANN generates better forecasting results than linear models for funds of all styles. In addition, our model outperforms that of Chiang et al. [Chiang WC, Urban TL, Baldridge GW. A neural network approach to mutual fund net asset value forecasting. Omega Int J Manage Sci 1996:24;205-215.] in predicting the performance of growth funds. We also employed a heuristic approach of variable selection via neural networks and compared it with the stepwise selection method of linear regression. Results are encouraging in that the reduced ANN models still outperform the linear models for growth and blend funds and yield similar results for value funds.

AB - This study utilizes an artificial neural network (ANN) approach to predict the performance of equity mutual funds that follow value, blend and growth investment styles. Using a multi-layer perceptron model and GRG2 nonlinear optimizer, fund-specific historical operating characteristics were used to forecast mutual funds' risk-adjusted return. Results show that ANN generates better forecasting results than linear models for funds of all styles. In addition, our model outperforms that of Chiang et al. [Chiang WC, Urban TL, Baldridge GW. A neural network approach to mutual fund net asset value forecasting. Omega Int J Manage Sci 1996:24;205-215.] in predicting the performance of growth funds. We also employed a heuristic approach of variable selection via neural networks and compared it with the stepwise selection method of linear regression. Results are encouraging in that the reduced ANN models still outperform the linear models for growth and blend funds and yield similar results for value funds.

UR - http://www.scopus.com/inward/record.url?scp=0013311467&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0013311467&partnerID=8YFLogxK

U2 - 10.1016/S0305-0483(98)00048-6

DO - 10.1016/S0305-0483(98)00048-6

M3 - Article

VL - 27

SP - 373

EP - 380

JO - Omega

JF - Omega

SN - 0305-0483

IS - 3

ER -