Abstract:
This study aims to develop a bankruptcy prediction model tailored to the
manufacturing sector in Indonesia, focusing on goods, services, luxury goods, and
apparel companies in the Indonesia Stock Exchange (IDX) from 2014 to 2023. The
model utilizes six financial ratios: Operating Cash Flow/Revenue, Working
Capital/Total Assets, Retained Earnings/Total Assets, Accounts Receivable/Current
Liabilities, Book Value of Equity/Book Value of Debt, and Inventory/Sales. Out of
83 data companiew, 16 were selected, with 8 experiencing significant financial
losses over 5-6 years and 8 others not. The model was developed using multiple
linear regression to calculate the relationship between financial ratios and the
likelihood of bankruptcy. The results indicate that Retained Earnings/Total Assets
and Operating Cash Flow/Revenue are significant predictors of bankruptcy, while
the other ratios are not significant. The model identifies threshold values that
categorize companies into three groups: bankrupt, grey area, and non-bankrupt,
with threshold values of -0.0670 and 0.2816. The model’s accuracy was tested using
the Binary Logistic method with SPSS, showing that when the grey area is
considered bankrupt, the accuracy without predictors is 68.8% and with predictors
is 100%. When the grey area is considered non-bankrupt, the accuracy without
predictors is 78.8% and with predictors is 100%. This study provides a valuable
tool for investors, creditors, and management to assess the financial health of
companies. However, it acknowledges limitations related to data normality and
multicollinearity and recommends further research to improve the model's
accuracy.
