Companies can’t afford to lose hard-won customers, but in truth some customers are more important to keep than others. In our recent research, Sunil Gupta and I show how to find them. A easy-to-digest summary of our approach was provided by Forbes a few years ago.

MANAGING CHURN TO MAXIMIZE PROFITS

Customer defection threatens many industries, prompting companies to deploy targeted, proactive customer retention programs and offers. A conventional approach has been to target customers either based on their predicted churn probability, or their responsiveness to a retention offer. However, both approaches ignore that some customers contribute more to the profitability of retention campaigns than others.

In a recent study, Sunil Gupta and I address this problem by defining a profit-based loss function to predict, for each customer, the financial impact of a retention intervention. This profit-based loss function aligns the objective of the estimation algorithm with the managerial goal of maximizing the campaign profit. It ensures (1) that customers are ranked based on the incremental impact of the intervention on churn and post-campaign cash flows, after accounting for the cost of the intervention and (2) that the model minimizes the cost of prediction errors by penalizing customers based on their expected profit lift. Finally, it provides a method to optimize the size of the retention campaign.

We show using two field experiments that our approach leads to significantly more profitable campaigns than competing models and differences can have substantial impact of firms’ revenues.

SMALL INTERVENTION, HIGH RETURNS

The benefits from a profit-based loss functions are substantial, but its implementation only has limited costs. What companies need is a small scale randomized control trial (so-called A/B test) where they randomly offer a retention incentive to some of their customers. Leveraging these data, the profit-based loss function will then identify which targets are most profitable.

While the cost of implementation of a small scale A/B test are reasonable, the extra revenues the approach generates are substantial. In our analysis, we find that our approach can boost firms’ overall revenues by at least 3%.

You can access the full manuscript via the following link: http://dx.doi.org/10.2139/ssrn.2964906