Exploring Data Segmentation and Donation Giving Behaviors

The main aim of the project was to build a machine learning model to predict if a person donates to the university or not. The prediction model uses the demographic information, professional information, educational qualification, and prior donation details as input features. The project flow includes tasks like data collection and cleaning, exploratory data analysis, selecting appropriate algorithms, training the model, and getting accurate predictions. I was able to develop a binary classification model using XGB Classifier with an ROC-AUC score of 0.92. The initial analysis was focused on understanding the demographics of people who donated continuously from 2015-2020. The analysis and the results should help the RAD team to understand the circumstances under which a prospect will donate, the relationship between giving amount and ask amount.