How can FP&A use AI to Obtain Forward-Looking Insights into Customer Loyalty?
An Interview with Jamie Cousin, FP&A Manager at ServiceMaster
What exactly leads to customer loyalty – and what can the business do to increase it? The FP&A team at ServiceMaster is searching for answers deep in the individual experiences and purchase histories of over 2 million customers with assistance from the new Artificial Intelligence capabilities embedded in Jedox software. Two months into the project, we caught up with Jamie Cousin, FP&A Manager at ServiceMaster, to talk about the team’s experiences, project results, and next steps ahead.
ServiceMaster has been a Jedox customer for over 3 years. How are you currently using the software?
We currently use Jedox as the hub to maintain and retrieve our financial data at ServiceMaster to fulfill both our external and internal reporting needs. Jedox has allowed us to be more efficient in gathering as well as reporting the data. We also have branch managers across North America that log into Jedox to view their profit and loss statements. They also use it annually to enter in their budget numbers, which we roll up into a consolidated view for tracking and creating various monthly analysis reports.
Jedox has been a very central part of our business today and we are frequently being challenged to come up with new ways to use it in our business applications.
Your latest FP&A project is looking at customer loyalty utilizing the new, embedded AI capabilities in Jedox. How did that get started?
Over the past two years, we have increased efforts to improve the customer experience gaining higher customer promoters. The AI functionality in Jedox provides a great opportunity to understand it and act proactively.
Why did you select this FP&A project to apply the AI capabilities in Jedox software?
Terminix has customers across North America with many different products and services for each customer. Our customer variables include different frequencies, payment methods, geography, climate, and application methods. Our customer volume and product attributes make it very hard to draw some type of conclusion. By using AI, we can take everything we know about our customers – both new and historically – and predict future behaviors.
What are some of the tangible results that you have seen from the AI project so far?
The objective was for AI to assist in predicting and analyzing customer loyalty. We loaded data to Jedox that was extracted into the AI software. This has allowed us to see exactly how the AI prediction for customer loyalty compares to actual loyalty and how closely those results have been aligned with each other.
One of the benefits was how quickly we were able to obtain results. We fed a very large amount of data into the model and within a very short project development were able to gain insight into the data that did not previously exist. We found features that you wouldn’t normally think correlate with customer loyalty or that were on our list but didn’t rank as highly.
Using AI, we have gained quicker insights with a higher confidence into relevant customer features – not only looking at financial measures but also looking at customers from an HR prospective or a marketing perspective. With faster predictions we can utilize the results that much quicker to determine any changes to our business processes, make those changes, and begin to see results even faster yet.
Which insights from AI into relevant customer features for loyalty surprised you the most?
The contract value was surprising. Others included tenure and whether the customer came to us with a problem or we proactively reached out to that customer with a preventative solution. Product mix was another feature that affected customer loyalty.
As a company, we have always focused so hard on service, service, service. We were so focused on thinking that everything was service-related that we hadn’t taken many of these other factors into consideration. The AI project sheds light on new features that could be causing the issues as opposed to our older way of thinking where we just assumed what was happening.
Where do you want to take the AI project from here?
I think now our next goal is the timing of customer detractors. We were very impressed with the results as far. We have detailed output down to the individual contract level. The next step now is determining when and why customer loyalty decreases to prevent to customer complaints and cancellations. As opposed to me saying, “Over the next year we are going to lose X number of customer’s confidence”, the next step would be to give more specific information to the sales and services teams. For example: “In the month of April we are going to lose this number of customer’s confidence in this particular area. Here is the action plan from the branch manager who is responsible for those customers and the technicians who service them. You need to touch base with each of them and follow through to ensure that they are not dissatisfied with service, price, or customer care at the end of the month.”
Jedox is looking forward to help ServiceMaster shed light on the question of “Why a customer stays loyal” through the available decision trees and different information showing the probability and range using the embedded AI capabilities. Jedox is dedicated to providing AI solutions that truly evolve with the ever changing needs of our customers and can be easily queried by FP&A with different data – month after month, week after week.
Discover how AI and predictive analytics make enterprise-wide planning smarter.
