Applied Machine Learning Project
Team 8 Members: Sumanth, Sharath, Navneeth, Bentic
Project Title: Predicting Financial Distress, using Regression models and a Stacking approach
In this project, we attempt to create a Regression model to predict when a company is in financial distress. Being able to predict companies close to financial distress will help investors make decisions to protect themselves, or invest more and help these companies prevent bankruptcy in advance because the collective number of failing companies can be regarded as an important indicator of the financial health and robustness of a country’s economy.
Kaggle Dataset Source: https://www.kaggle.com/shebrahimi/financial-distress/code
Financial Distress dataset:https://github.com/bsebast2/AppliedMLProject/blob/main/Financial%20Distress.csv
Link to our Python Notebook: https://github.com/bsebast2/AppliedMLProject/blob/main/Applied_ML_edited_v2%20(2).ipynb
Link to our Final Report: https://github.com/bsebast2/AppliedMLProject/blob/main/AML%20Final%20Report.pdf
Instructions to run Streamlit :
Use three files : predictive_model.py, function.py, FinancialDistress.csv
Code: "streamlit run predictive_model.py"