We live in a time where decentralized finance has been on the rise and more businesses have been closing than ever before. My last post analyzed posts from a group dedicated to the downfall of rich hedge fund investors. Now I will be doing a different type of analysis.
I created a model to predict the likelihood of a business going bankrupt in Taiwan. My data set came from Kaggle. I did the usual imports of essential libraries for EDA and modeling. Fortunately my dataset has no errors. After doublechecking that the data had no issues, I did some exploratory data analysis to identify any potential trends of collinearity between features. There were no significant correlations or signs of collinearity. I then began developing a model. I used a handy method from SKLearn called “feature selection”. It algorithmically selects the most useful features out of a set of data. I chose to stick with the top 50 features for my model to train from. I will add more analysis to this project in my next post.