Mortgages, student and auto loans, and debt consolidation are just a few examples of credit and loans that people seek online. Peer-to-peer lending services such as Loans Canada and Mogo let investors loan people money without using a bank. However, because investors always want to mitigate risk, it would be helpful to predict credit risk with machine learning techniques. This experiment attempts to predict credit risk based on various machine learning models, to find out the best performing model amongst them. Credit risk is inherently imbalanced classification problem (i.e., there will always be more number of good customers than the number of at-risk loans), so along with the exploratory analysis to understand the data and modeling for prediction, we need to balance the data before applying machine learning models. The following experiment presents the study on Credit risk and concentrates on, first on correct classification of Credit Risky customers. And second, more on reducing False Negatives, i.e., on reducing the classification error of classifying risky customers as non-risky.