FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron

Ahmed M. Khedr; Magdi El Bannany; Abdul Wahid A. Saif

doi:10.1109/SSD54932.2022.9955722

FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron

Ahmed M. Khedr, Magdi El Bannany, Abdul Wahid A. Saif

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Developing a reliable financial distress prediction model has been a long-standing research area. Recently, machine learning algorithms have been increasingly popular in the area. In this paper, a hybrid approach of Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP) for Financial Distress Prediction (FDP) (FDP-GAMLP) is proposed. FDP-GAMLP emphasizes on GA-based tuning of the four major hyper-parameters, namely network width, network depth, network optimizer, and dense layer activation function, which can influence on whether the algorithm explodes or converges. An improved GA is utilized to optimize the MLP model's hyper-parameters for better prediction. The prediction performance is evaluated using real data set with samples of companies from countries in Middle East region. The resampling technique using k-fold evaluation metrics is adopted to get unbiased and most accurate results. The simulation results show that FDP-GAMLP outperforms the classical machine learning models in terms of predictive accuracy.

Original language	English
Title of host publication	2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	361-366
Number of pages	6
ISBN (Electronic)	9781665471084
DOIs	https://doi.org/10.1109/SSD54932.2022.9955722
State	Published - 2022
Event	19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022 - Setif, Algeria Duration: 6 May 2022 → 10 May 2022

Publication series

Name	2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

Conference

Conference	19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022
Country/Territory	Algeria
City	Setif
Period	6/05/22 → 10/05/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Financial Distress Prediction
Genetic Algorithm
Multi-Layer Perceptron
Optimized deep learning model

ASJC Scopus subject areas

Instrumentation
Computer Networks and Communications
Hardware and Architecture
Signal Processing
Electrical and Electronic Engineering
Mechanical Engineering
Safety, Risk, Reliability and Quality

Access to Document

10.1109/SSD54932.2022.9955722

Cite this

Khedr, A. M., Bannany, M. E., & Saif, A. W. A. (2022). FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron. In 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022 (pp. 361-366). (2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD54932.2022.9955722

Khedr, Ahmed M. ; Bannany, Magdi El ; Saif, Abdul Wahid A. / FDP-GAMLP : New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron. 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 361-366 (2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022).

@inproceedings{39d0de75e3454caa912237e957d77661,

title = "FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron",

abstract = "Developing a reliable financial distress prediction model has been a long-standing research area. Recently, machine learning algorithms have been increasingly popular in the area. In this paper, a hybrid approach of Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP) for Financial Distress Prediction (FDP) (FDP-GAMLP) is proposed. FDP-GAMLP emphasizes on GA-based tuning of the four major hyper-parameters, namely network width, network depth, network optimizer, and dense layer activation function, which can influence on whether the algorithm explodes or converges. An improved GA is utilized to optimize the MLP model's hyper-parameters for better prediction. The prediction performance is evaluated using real data set with samples of companies from countries in Middle East region. The resampling technique using k-fold evaluation metrics is adopted to get unbiased and most accurate results. The simulation results show that FDP-GAMLP outperforms the classical machine learning models in terms of predictive accuracy.",

keywords = "Financial Distress Prediction, Genetic Algorithm, Multi-Layer Perceptron, Optimized deep learning model",

author = "Khedr, \{Ahmed M.\} and Bannany, \{Magdi El\} and Saif, \{Abdul Wahid A.\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022 ; Conference date: 06-05-2022 Through 10-05-2022",

year = "2022",

doi = "10.1109/SSD54932.2022.9955722",

language = "English",

series = "2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "361--366",

booktitle = "2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022",

address = "United States",

}

Khedr, AM, Bannany, ME & Saif, AWA 2022, FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron. in 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022. 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022, Institute of Electrical and Electronics Engineers Inc., pp. 361-366, 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022, Setif, Algeria, 6/05/22. https://doi.org/10.1109/SSD54932.2022.9955722

FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron. / Khedr, Ahmed M.; Bannany, Magdi El; Saif, Abdul Wahid A.
2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 361-366 (2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - FDP-GAMLP

T2 - 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

AU - Khedr, Ahmed M.

AU - Bannany, Magdi El

AU - Saif, Abdul Wahid A.

PY - 2022

Y1 - 2022

N2 - Developing a reliable financial distress prediction model has been a long-standing research area. Recently, machine learning algorithms have been increasingly popular in the area. In this paper, a hybrid approach of Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP) for Financial Distress Prediction (FDP) (FDP-GAMLP) is proposed. FDP-GAMLP emphasizes on GA-based tuning of the four major hyper-parameters, namely network width, network depth, network optimizer, and dense layer activation function, which can influence on whether the algorithm explodes or converges. An improved GA is utilized to optimize the MLP model's hyper-parameters for better prediction. The prediction performance is evaluated using real data set with samples of companies from countries in Middle East region. The resampling technique using k-fold evaluation metrics is adopted to get unbiased and most accurate results. The simulation results show that FDP-GAMLP outperforms the classical machine learning models in terms of predictive accuracy.

AB - Developing a reliable financial distress prediction model has been a long-standing research area. Recently, machine learning algorithms have been increasingly popular in the area. In this paper, a hybrid approach of Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP) for Financial Distress Prediction (FDP) (FDP-GAMLP) is proposed. FDP-GAMLP emphasizes on GA-based tuning of the four major hyper-parameters, namely network width, network depth, network optimizer, and dense layer activation function, which can influence on whether the algorithm explodes or converges. An improved GA is utilized to optimize the MLP model's hyper-parameters for better prediction. The prediction performance is evaluated using real data set with samples of companies from countries in Middle East region. The resampling technique using k-fold evaluation metrics is adopted to get unbiased and most accurate results. The simulation results show that FDP-GAMLP outperforms the classical machine learning models in terms of predictive accuracy.

KW - Financial Distress Prediction

KW - Genetic Algorithm

KW - Multi-Layer Perceptron

KW - Optimized deep learning model

UR - https://www.scopus.com/pages/publications/85143780238

U2 - 10.1109/SSD54932.2022.9955722

DO - 10.1109/SSD54932.2022.9955722

M3 - Conference contribution

AN - SCOPUS:85143780238

T3 - 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

SP - 361

EP - 366

BT - 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 6 May 2022 through 10 May 2022

ER -

Khedr AM, Bannany ME, Saif AWA. FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron. In 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 361-366. (2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022). doi: 10.1109/SSD54932.2022.9955722

FDP-GAMLP: New Financial Distress Prediction Technique based on Genetic Algorithm and Multi-Layer Perceptron

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this