XGBoost model of credit card fraud detection

Anytime an employee is hired, it is a massive gamble for the company. Ensuring they did the right job, they work feverishly, checking the resume, conducting interview after interview, maybe an assessment or LeetCode challenge to hire an employee, and desperate that they made the right choice out of the other 500 applicants. So much effort has gone into one person. The last thing this company needs is another employee gone, creating a vacancy to fill. So, what is it that makes an employee leave? How can we as a company predict and see what may influence an employee to leave, so before they do, we handle it and keep them satisfied? This data story will walk that path, and in the end, build a machine learning model to predict it in the future.

Smaller banks face significant financial risks when issuing loans due to their limited capital reserves compared to larger banks. They must be highly selective in their lending practices, as loan defaults can have a substantial negative impact on their financial stability. This project aims to address this challenge by training multiple machine learning models on loan data to identify the key factors that predict loan defaults. By understanding these critical indicators, smaller banks can make more informed lending decisions and mitigate potential losses.