Research indicates that acquiring new customers can cost up to five times more than retaining existing ones. Furthermore, enhancing customer retention by just 5% can potentially boost profits by up to 95%. In this context, a Non-profit organization aimed to pinpoint which of their regular donors were at risk of discontinuing their contributions, enabling timely intervention.
While there’s an abundance of data at hand, it’s tempting to initiate rule-based predictions by observing apparent trends, such as payment methods or membership duration. However, rule-based systems can be complex and demanding to maintain, especially in a constantly evolving market.
To enhance the precision of churn predictions, it’s imperative to consider a broader set of variables, including age, donor’s journey to monthly contributions, payment method, donation amount, lifetime value, and gender, among others. Employing Machine Learning via Allyy.io provides a robust solution for anticipating donor churn. Through a comprehensive analysis of historical data, Allyy adeptly forecasts which donors are on the brink of churning. Key determinants from the NGO’s data revealed that the duration of monthly donations and the chosen payment method were pivotal indicators. Within days, a churn prediction model was built, refined, and implemented. The results split the donor base into distinct risk categories:
4% high risk
27% medium risk
69% low risk
With this structured insight, NGOs are better equipped to bolster their retention strategies, potentially surpassing the 5% enhancement mark. For donors identified as high or medium risk, targeted interventions, such as personalized calls or loyalty-enhancing letters and emails, are then strategically deployed to reinforce their commitment.
If you have the data
– you might as well get the most out of it, and in most cases, that is with Allyy.io