Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195805,
        author = {Mrs. Sandhya Rani and Kompally Poorvika and Bolledu Sri Chandana and Manda Samyuktha and Shate Krishna Shree},
        title = {Improving Bankruptcy Prediction Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1141-1147},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195805},
        abstract = {Proper prediction of bankruptcy is a key component in creditor, investor, enterprise, and policy maker’s decision-making frameworks. Such forecasting mechanisms can also be used to curb wider undesirable impacts on the economy and society by facilitating a more accurate assessment of individual risks. However, the classical bankruptcy forecasting frameworks are often limited by the major assumptions; they assume linear correlation and, therefore, perform poorly in the case of an extremely lopsided financial data set. In order to address these limitations, the current paper proposes a modern machine-learning model tested on the Taiwan Bankruptcy Prediction Dataset. To successfully reduce the problem of class imbalance and enhance the overall predictive accuracy, a set of approaches were cross-validated, with special attention given to the usage of the Synthetic Minority Over Sampling Technique (SMOTE) in combination with the Random Forest classifiers. The usefulness of the proposed model in practice is demonstrated by building an easy-to-use web-based dashboard. The application was created with Python, Pandas, Scikit-Learn, and Stream lit as it allows users to upload financial data automatically and obtain instant and probabilistic estimates of the risk of bankruptcy. In the end, this system fills the gap between complex financial trends and evidence-based and useful insights, thus providing a powerful tool that helps financial institutions and investors in decision making.},
        keywords = {Bankruptcy prediction, machine learning, SMOTE, random forest classification, cross validation, accuracy.},
        month = {April},
        }