Financial Distress Prediction with Optimized Artificial Neural Networks: A Comparative Study of Optimization Algorithms

DOI

10.2991/978-94-6463-878-3_23How to use a DOI?

Keywords

Artificial Neural Networks; Financial Distress; Optimization Algorithms

Abstract

Deep learning, a prominent branch of machine learning, has emerged as a powerful predictive modeling approach known for its high accuracy. One of its most essential components is the Artificial Neural Network (ANN), which emulates the human brain’s neural structure, comprising thousands of interconnected neurons. Previous studies have highlighted the effectiveness of ANN in predicting financial distress, a condition indicating a company’s financial difficulties and often serving as an early warning sign of potential bankruptcy. However, the predictive performance of ANN models is highly influenced by the optimization algorithms. Various optimization algorithms have been developed to improve ANN performance, including Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMSProp), Adaptive Gradient Descent (AdaGrad), Adadelta, and Adaptive Moment Estimation (Adam) optimizer. The application of these optimizers can yield varying model performance depending on the specific dataset or case. This study aims to apply and compare different ANN optimization algorithms to determine the most suitable one for enhancing the predictive performance of financial distress models in the Indonesian property and real estate sector. The findings reveal that the Adam optimizer outperforms other optimization algorithms, achieving the highest accuracy and superior AUC in predicting financial distress among companies in this sector.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ni Wayan Dewinta Ayuni
AU  - I Made Wijana
AU  - I Made Dwijendra Sulastra
AU  - Ni Nengah Lasmini
AU  - Agus Adi Putrawan
PY  - 2025
DA  - 2025/10/31
TI  - Financial Distress Prediction with Optimized Artificial Neural Networks: A Comparative Study of Optimization Algorithms
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 193
EP  - 202
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_23
DO  - 10.2991/978-94-6463-878-3_23
ID  - Ayuni2025
ER  -