Company bankruptcy prediction framework based on the most influential features using XGBoost and stacking ensemble learning
| Main Authors: | Much Aziz Muslim, Yosza Dasril |
|---|---|
| Format: | Article Journal |
| Terbitan: |
, 2021
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/5720078 |
Daftar Isi:
- Company bankruptcy is often a very big problem for companies. The impactof bankruptcy can cause losses to elements of the company such as owners,investors, employees, and consumers. One way to prevent bankruptcy is to predict the possibility of bankruptcy based on the company's financial data.Therefore, this study aims to find the best predictive model or method topredict company bankruptcy using the dataset from Polish companiesbankruptcy. The prediction analysis process uses the best feature selectionand ensemble learning. The best feature selection is selected using feature importance to XGBoost with a weight value filter of 10. The ensemblelearning method used is stacking. Stacking is composed of the base modeland meta learner. The base model consists of K-nearest neighbor, decisiontree, support vector machines (SVM), and random forest, while the metalearner used is LightGBM. The stacking model accuracy results can outperform the base model accuracy with an accuracy rate of 97%.