Deep learning-based corporate performance prediction model considering technical capability

Joonhyuck Lee, Dong Sik Jang, Sangsung Park

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Many studies have predicted the future performance of companies for the purpose of making investment decisions. Most of these are based on the qualitative judgments of experts in related industries, who consider various financial and firm performance information. With recent developments in data processing technology, studies have started to use machine learning techniques to predict corporate performance. For example, deep neural network-based prediction models are again attracting attention, and are now widely used in constructing prediction and classification models. In this study, we propose a deep neural network-based corporate performance prediction model that uses a company's financial and patent indicators as predictors. The proposed model includes an unsupervised learning phase and a fine-tuning phase. The learning phase uses a restricted Boltzmann machine. The fine-tuning phase uses a backpropagation algorithm and a relatively up-to-date training data set that reflects the latest trends in the relationship between predictors and corporate performance.

Original languageEnglish
Article number899
JournalSustainability (Switzerland)
Volume9
Issue number6
DOIs
Publication statusPublished - 2017 May 26

Fingerprint

learning
prediction
performance
Tuning
neural network
data processing technology
Industry
Unsupervised learning
Backpropagation algorithms
Learning systems
patent
Deep learning
industry
expert
firm
trend
Deep neural networks

Keywords

  • Corporate performance prediction
  • Deep belief network
  • Deep learning
  • Prediction model
  • Technical indicator

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Renewable Energy, Sustainability and the Environment
  • Management, Monitoring, Policy and Law

Cite this

Deep learning-based corporate performance prediction model considering technical capability. / Lee, Joonhyuck; Jang, Dong Sik; Park, Sangsung.

In: Sustainability (Switzerland), Vol. 9, No. 6, 899, 26.05.2017.

Research output: Contribution to journalArticle

@article{e8852b0e57aa4846b6ebb2673dd6780e,
title = "Deep learning-based corporate performance prediction model considering technical capability",
abstract = "Many studies have predicted the future performance of companies for the purpose of making investment decisions. Most of these are based on the qualitative judgments of experts in related industries, who consider various financial and firm performance information. With recent developments in data processing technology, studies have started to use machine learning techniques to predict corporate performance. For example, deep neural network-based prediction models are again attracting attention, and are now widely used in constructing prediction and classification models. In this study, we propose a deep neural network-based corporate performance prediction model that uses a company's financial and patent indicators as predictors. The proposed model includes an unsupervised learning phase and a fine-tuning phase. The learning phase uses a restricted Boltzmann machine. The fine-tuning phase uses a backpropagation algorithm and a relatively up-to-date training data set that reflects the latest trends in the relationship between predictors and corporate performance.",
keywords = "Corporate performance prediction, Deep belief network, Deep learning, Prediction model, Technical indicator",
author = "Joonhyuck Lee and Jang, {Dong Sik} and Sangsung Park",
year = "2017",
month = "5",
day = "26",
doi = "10.3390/su9060899",
language = "English",
volume = "9",
journal = "Sustainability",
issn = "2071-1050",
publisher = "MDPI AG",
number = "6",

}

TY - JOUR

T1 - Deep learning-based corporate performance prediction model considering technical capability

AU - Lee, Joonhyuck

AU - Jang, Dong Sik

AU - Park, Sangsung

PY - 2017/5/26

Y1 - 2017/5/26

N2 - Many studies have predicted the future performance of companies for the purpose of making investment decisions. Most of these are based on the qualitative judgments of experts in related industries, who consider various financial and firm performance information. With recent developments in data processing technology, studies have started to use machine learning techniques to predict corporate performance. For example, deep neural network-based prediction models are again attracting attention, and are now widely used in constructing prediction and classification models. In this study, we propose a deep neural network-based corporate performance prediction model that uses a company's financial and patent indicators as predictors. The proposed model includes an unsupervised learning phase and a fine-tuning phase. The learning phase uses a restricted Boltzmann machine. The fine-tuning phase uses a backpropagation algorithm and a relatively up-to-date training data set that reflects the latest trends in the relationship between predictors and corporate performance.

AB - Many studies have predicted the future performance of companies for the purpose of making investment decisions. Most of these are based on the qualitative judgments of experts in related industries, who consider various financial and firm performance information. With recent developments in data processing technology, studies have started to use machine learning techniques to predict corporate performance. For example, deep neural network-based prediction models are again attracting attention, and are now widely used in constructing prediction and classification models. In this study, we propose a deep neural network-based corporate performance prediction model that uses a company's financial and patent indicators as predictors. The proposed model includes an unsupervised learning phase and a fine-tuning phase. The learning phase uses a restricted Boltzmann machine. The fine-tuning phase uses a backpropagation algorithm and a relatively up-to-date training data set that reflects the latest trends in the relationship between predictors and corporate performance.

KW - Corporate performance prediction

KW - Deep belief network

KW - Deep learning

KW - Prediction model

KW - Technical indicator

UR - http://www.scopus.com/inward/record.url?scp=85020002265&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020002265&partnerID=8YFLogxK

U2 - 10.3390/su9060899

DO - 10.3390/su9060899

M3 - Article

VL - 9

JO - Sustainability

JF - Sustainability

SN - 2071-1050

IS - 6

M1 - 899

ER -