Financial distress prediction for batik small and medium enterprises credit financing based on deep learning algorithm

Abstract

One of the biggest obstacles that any finance provider has when evaluating a borrower's creditworthiness is the prediction of financial trouble. The credit decision-making process is made more difficult for small and medium enterprises (SMEs) due to their inherent ambiguity, which raises financing costs and lowers the chance of approval. In order to estimate a binomial classifier for predicting financial hardship using logistic regression (LR), extreme gradient boosting (XGBoost), and artificial neural network (ANN) techniques, this study examines data from batik SMEs in Pekalongan city. Financial ratios predict the first period and grow in a multi-period model based on temporal factors, credit history, and age. Financial distress is defined as a substantial obstacle to a business's capacity to pay its debts as opposed to the potential for bankruptcy. The long short-term memory (LSTM) algorithm with more variables yields the best prediction accuracy. The study's conclusion indicates that in order to guarantee the accuracy of financial distress prediction, the time at risk must be adjusted.