A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised

The financial performance of a listed company is a common concern for shareholders, creditors, employees, securities analysts, and the government. Measuring and forecasting financial performance informs stakeholders about a company's overall well-being. In this study, we propose a hybrid approa...

Full description

Saved in:
Bibliographic Details
Main Author: Jiadong Teng
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Systems Science & Control Engineering
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2024.2305411
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846118852996366336
author Jiadong Teng
author_facet Jiadong Teng
author_sort Jiadong Teng
collection DOAJ
description The financial performance of a listed company is a common concern for shareholders, creditors, employees, securities analysts, and the government. Measuring and forecasting financial performance informs stakeholders about a company's overall well-being. In this study, we propose a hybrid approach that combines grey relation analysis, Self-Organized Mapping (SOM) neural network, and convolutional neural network to assess the financial performance of listed companies. Grey relation analysis measures financial performance, SOM neural network clusters, and convolutional neural network forecasts. Compared to other models, the hybrid convolutional neural network model has a better predictive effect, accurately forecasting the financial status of listed companies. Findings also reveal that 70.93 percent of listed companies in agriculture, forestry, husbandry, and fisheries have a poor financial status.
format Article
id doaj-art-f1ada50b63ac40d6b8dcb92a0c67e986
institution Kabale University
issn 2164-2583
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Systems Science & Control Engineering
spelling doaj-art-f1ada50b63ac40d6b8dcb92a0c67e9862024-12-17T09:06:12ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832024-12-0112110.1080/21642583.2024.2305411A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervisedJiadong Teng0College of Computer and Information Science, Southwest University, Chongqing, People’s Republic of ChinaThe financial performance of a listed company is a common concern for shareholders, creditors, employees, securities analysts, and the government. Measuring and forecasting financial performance informs stakeholders about a company's overall well-being. In this study, we propose a hybrid approach that combines grey relation analysis, Self-Organized Mapping (SOM) neural network, and convolutional neural network to assess the financial performance of listed companies. Grey relation analysis measures financial performance, SOM neural network clusters, and convolutional neural network forecasts. Compared to other models, the hybrid convolutional neural network model has a better predictive effect, accurately forecasting the financial status of listed companies. Findings also reveal that 70.93 percent of listed companies in agriculture, forestry, husbandry, and fisheries have a poor financial status.https://www.tandfonline.com/doi/10.1080/21642583.2024.2305411Grey relation analysisSOM neural networkconvolutional neural networkfinancial performancehybrid approach
spellingShingle Jiadong Teng
A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
Systems Science & Control Engineering
Grey relation analysis
SOM neural network
convolutional neural network
financial performance
hybrid approach
title A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
title_full A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
title_fullStr A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
title_full_unstemmed A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
title_short A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised
title_sort hybrid approach of deep learning to forecast financial performance from unsupervised to supervised
topic Grey relation analysis
SOM neural network
convolutional neural network
financial performance
hybrid approach
url https://www.tandfonline.com/doi/10.1080/21642583.2024.2305411
work_keys_str_mv AT jiadongteng ahybridapproachofdeeplearningtoforecastfinancialperformancefromunsupervisedtosupervised
AT jiadongteng hybridapproachofdeeplearningtoforecastfinancialperformancefromunsupervisedtosupervised