The document discusses building a machine learning model to predict customer redemptions from mutual funds. It analyzes historical transaction data to identify predictive variables and build a logistic regression model to classify customers as likely to redeem or not redeem. The model achieves 76% accuracy on test data and 71% on validation data. Future work is proposed to use uplift modeling to optimize sales and reduce costs by targeting customers most likely to purchase after incentives. Cross-sell analysis is also proposed to identify customers with equity holdings likely to purchase mutual funds based on demographic and transaction characteristics.