This document presents a video presentation on using data analytics for loan prediction based on customer behavior. It explores a dataset from Kaggle containing information like income, age, experience, marital status, and risk flags to predict whether a consumer is likely to default on a loan. The presentation discusses collecting and exploring the data, identifying issues like a numeric class label that were addressed, and analyzing which attributes like risk flag and credit worthiness were most correlated to the class label and predictive of defaults. Attributes like marital status showed little impact. The goal is to provide insights into customer behavior for accurate loan prediction in the financial industry.