Lending club receives many loan applications. From companies point of view, lending loan always have high risk associated with it. Our project is to identify these risky factors which company can take into consideration while lending loan to a borrower.

• General Info
• Technologies Used
• Conclusions
• Acknowledgments

• Our project is about finding risk factors associated with a loan borrower
• We are trying to solve loan risk factor for leading companies
• CSV file(Common-separated values)

• In general it is observed people with loan tenure of 60months have high chances of default compared to loan tenure of 36months.
• It is also observed, people belonging to grades C,D,E & F have high tendency to default.
• It is also observed that people for whom income source was not verified they tend to default.
• Other observation is that people who stay on rent or have their house as mortgage have a tendency to default.
• In general it was observed loan taken for 'small businesses' are risky, followed by 'debt consolidation'.
• Also, people with dti between 15-20 are more likely to default.
• People with loan interest rate higher than 10% also have a tendency to default.
• One more interesting observation was people from West; out of four USA regions - West, South, Northeast, Midwest; have little higher tendency to default when compared to people from remaining three regions.
• REFER TO THE EXCEL FILE FOR DETAILED RECOMMENDATIONS MATRIX (File Name: Recommendation_Matrix.xlsx). Yellow cells in this excel file indicate that there is no recommendation for that particular combination. Or in other words this pair of variables is not related to give any recommendation.

• libraries - ipython, pandas, numpy, seaborn, matplotlib, itertools

Give credit here.

• References if any For information about US States and their Regions: https://www.istockphoto.com/vector/map-of-united-states-split-into-census-regions-and-divisions-gm1218022040-355768080

Created by @ameycancode