The Effect of Imbalanced Data and Parameter Selection via Genetic Algorithm Long Short-Term Memory (LSTM) for Financial Distress Prediction

Financial companies are grappling with a burning issue about bankruptcy prediction. There are many methods for bankruptcy prediction, including statistical models and machine learning. Real-life datasets are often imbalanced with high dimensionality. Therefore, it is challenging to train a robust mo...

Full description

Saved in:
Bibliographic Details
Published in:IAENG international journal of applied mathematics 2023-09, Vol.53 (3), p.25-38
Main Authors: Adisa, Juliana Adeola, Ojo, Samuel, Owolawi, Pius Adewale, Pretorius, Agnieta, Ojo, Sunday Olusegun
Format: Article
Language:English
Subjects:
Bankruptcy
Classification
Decision trees
Financial analysis
Genetic algorithms
Machine learning
Model accuracy
Neural networks
Optimization
Optimization techniques
Oversampling
Parameters
Securities markets
Statistical models
Support vector machines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Financial companies are grappling with a burning issue about bankruptcy prediction. There are many methods for bankruptcy prediction, including statistical models and machine learning. Real-life datasets are often imbalanced with high dimensionality. Therefore, it is challenging to train a robust model to predict bankruptcy. Thus, we first applied an oversampling technique known as the Synthetic Minority Oversampling Technique (SMOTE) to reduce the skewness of the data. The balanced data was trained with the baseline models, the ensemble classifiers using different combination methods and the long short-term memory (LSTM) model. In addition, we employed an optimization technique called a genetic algorithm (GA) to optimize and determine the learning parameters of an LSTM network. We further determine the effects of using different training/testing ratios on the developed models. An autoencoder long short-term memory (LSTM) model was developed to extract the best feature representation of the input data. A comparative analysis was carried out between the LSTM-GA and autoencoder-LSTM. The results show that the improved LSTM-GA model with an accuracy of 98.11% performs better than other models. Overall, the research work concluded that all models and LSTM have good performances, while the optimized LSTM model via genetic algorithm outperforms the classical machine learning models.
ISSN:1992-9978
1992-9986