This case study analyzed 12,100 Canadian personal loan applications that were collected by Comparewise, an online loan introducer, from 2022-2023. The objective of the study was to identify statistically significant variables that affected loan outcome prediction, develop a model to predict approval or disapproval of loan application by lenders, and determine the accuracy of the model and how the level of accuracy can be interpreted in the context of Comparewise and their lender partners. The findings were that loan application approval/dissaproval status was able to be predicted using a Bayesian Search Cross-Validation model to achieve a high level of accuracy with relatively few fits. These significant findings can be implemented by Comparewise in their personal loan application processes to notify customers in real-time of their predicted application approval/disapproval and improve the quality of leads Comparewise provides to their lender partners to become a preferred partner in the Canadian fintech industry.