Neural network DEA for measuring the efficiency of mutual funds

Payam Hanafizadeh*, Hamid Reza Khedmatgozar, Ali Emrouznejad, Mojtaba Derakhshan

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Efficiency in the mutual fund (MF), is one of the issues that has attracted many investors in countries with advanced financial market for many years. Due to the need for frequent study of MF's efficiency in short-term periods, investors need a method that not only has high accuracy, but also high speed. Data envelopment analysis (DEA) is proven to be one of the most widely used methods in the measurement of the efficiency and productivity of decision making units (DMUs). DEA for a large dataset with many inputs/outputs would require huge computer resources in terms of memory and CPU time. This paper uses neural network back-ropagation DEA in measurement of mutual funds efficiency and shows the requirements, in the proposed method, for computer memory and CPU time are far less than that needed by conventional DEA methods and can therefore be a useful tool in measuring the efficiency of a large set of MFs.

Original languageEnglish
Pages (from-to)255-269
Number of pages15
JournalInternational Journal of Applied Decision Sciences
Volume7
Issue number3
DOIs
Publication statusPublished - 7 Jul 2014

Fingerprint

Data envelopment analysis
Neural networks
Mutual funds
Investors
Decision making units
Resources
Financial markets
Productivity

Keywords

  • back-ropagation DEA
  • data envelopment analysis
  • DEA
  • large dataset
  • mutual fund
  • neural network

Cite this

Hanafizadeh, Payam ; Reza Khedmatgozar, Hamid ; Emrouznejad, Ali ; Derakhshan, Mojtaba. / Neural network DEA for measuring the efficiency of mutual funds. In: International Journal of Applied Decision Sciences. 2014 ; Vol. 7, No. 3. pp. 255-269.
@article{6dcb0944f9ff46a4831b1750e581fea0,
title = "Neural network DEA for measuring the efficiency of mutual funds",
abstract = "Efficiency in the mutual fund (MF), is one of the issues that has attracted many investors in countries with advanced financial market for many years. Due to the need for frequent study of MF's efficiency in short-term periods, investors need a method that not only has high accuracy, but also high speed. Data envelopment analysis (DEA) is proven to be one of the most widely used methods in the measurement of the efficiency and productivity of decision making units (DMUs). DEA for a large dataset with many inputs/outputs would require huge computer resources in terms of memory and CPU time. This paper uses neural network back-ropagation DEA in measurement of mutual funds efficiency and shows the requirements, in the proposed method, for computer memory and CPU time are far less than that needed by conventional DEA methods and can therefore be a useful tool in measuring the efficiency of a large set of MFs.",
keywords = "back-ropagation DEA, data envelopment analysis, DEA, large dataset, mutual fund, neural network",
author = "Payam Hanafizadeh and {Reza Khedmatgozar}, Hamid and Ali Emrouznejad and Mojtaba Derakhshan",
year = "2014",
month = "7",
day = "7",
doi = "10.1504/IJADS.2014.063229",
language = "English",
volume = "7",
pages = "255--269",
journal = "International Journal of Applied Decision Sciences",
issn = "1755-8077",
publisher = "Inderscience Enterprises Ltd.",
number = "3",

}

Neural network DEA for measuring the efficiency of mutual funds. / Hanafizadeh, Payam; Reza Khedmatgozar, Hamid; Emrouznejad, Ali; Derakhshan, Mojtaba.

In: International Journal of Applied Decision Sciences, Vol. 7, No. 3, 07.07.2014, p. 255-269.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network DEA for measuring the efficiency of mutual funds

AU - Hanafizadeh, Payam

AU - Reza Khedmatgozar, Hamid

AU - Emrouznejad, Ali

AU - Derakhshan, Mojtaba

PY - 2014/7/7

Y1 - 2014/7/7

N2 - Efficiency in the mutual fund (MF), is one of the issues that has attracted many investors in countries with advanced financial market for many years. Due to the need for frequent study of MF's efficiency in short-term periods, investors need a method that not only has high accuracy, but also high speed. Data envelopment analysis (DEA) is proven to be one of the most widely used methods in the measurement of the efficiency and productivity of decision making units (DMUs). DEA for a large dataset with many inputs/outputs would require huge computer resources in terms of memory and CPU time. This paper uses neural network back-ropagation DEA in measurement of mutual funds efficiency and shows the requirements, in the proposed method, for computer memory and CPU time are far less than that needed by conventional DEA methods and can therefore be a useful tool in measuring the efficiency of a large set of MFs.

AB - Efficiency in the mutual fund (MF), is one of the issues that has attracted many investors in countries with advanced financial market for many years. Due to the need for frequent study of MF's efficiency in short-term periods, investors need a method that not only has high accuracy, but also high speed. Data envelopment analysis (DEA) is proven to be one of the most widely used methods in the measurement of the efficiency and productivity of decision making units (DMUs). DEA for a large dataset with many inputs/outputs would require huge computer resources in terms of memory and CPU time. This paper uses neural network back-ropagation DEA in measurement of mutual funds efficiency and shows the requirements, in the proposed method, for computer memory and CPU time are far less than that needed by conventional DEA methods and can therefore be a useful tool in measuring the efficiency of a large set of MFs.

KW - back-ropagation DEA

KW - data envelopment analysis

KW - DEA

KW - large dataset

KW - mutual fund

KW - neural network

UR - http://www.scopus.com/inward/record.url?scp=84904011725&partnerID=8YFLogxK

UR - http://www.inderscience.com/offer.php?id=63229

U2 - 10.1504/IJADS.2014.063229

DO - 10.1504/IJADS.2014.063229

M3 - Article

AN - SCOPUS:84904011725

VL - 7

SP - 255

EP - 269

JO - International Journal of Applied Decision Sciences

JF - International Journal of Applied Decision Sciences

SN - 1755-8077

IS - 3

ER -