Terminix gains customer retention insights with AI

Forecasting key financial metrics for the company is just one of the many responsibilities of the FP&A team at Terminix. Jamie Cousin, the FP&A Manager, and her team are tasked with not only estimating the number of customers who may cancel within a given amount of time but also identifying these customers and the factors that influence their decision. More importantly, she is being asked what actions can be taken within the company to prevent cancellations and increase customer loyalty in the process. Cousin and her team knew that service was a driver, but wanted to understand if any other factors influence customer loyalty in a significant way. Terminix has plenty of good data to help answer these questions, but the sheer volume of customers and multiple product attributes made it difficult for Terminix to draw firm conclusions.

To take its analytics capabilities to the next level, the FP&A team decided to run a pilot project using the new AI capabilities directly embedded in Jedox software. Terminix has used Jedox over the past three years as the hub to maintain and retrieve financial data and fulfill its external and internal reporting needs more efficiently. “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,” Cousin explains. When asked about why the team selected Jedox for this project, Steve Krantz, lead technical resource for Jedox at Terminix, explained, “Jedox is a very user-friendly tool, and our business community loves it. It was a natural fit for us to turn to Jedox. The Jedox solution makes AI very easy and intuitive for non-techies. It’s just a matter of providing a dataset and making a few tweaks here and there in a very straightforward way to define ‘features’ based on that data,” says Krantz.

Kevin Kennedy, business systems manager at Terminix, who helped implement Jedox three years ago, assisted the team as the subject matter expert during the AI deployment. “For our AI project, in particular, we are managing masses of data from several sources,” said Kennedy. “Jedox is a great solution to assemble the right data as well as set, track, and monitor it over time. Instead of using an ERP system and different budget ledgers, we are using Jedox because it is much easier to change and manipulate the data. There is also quicker turnaround because FP&A is in control of it,” Kennedy concluded.

Having good data and the ability to pull huge amounts of this data together rapidly is essential in any AI project. What is just as important, however, is having someone who truly understands the data itself from a technical and business perspective. For the Jedox AI project at Terminix, this data expert is Kevin Kennedy. The first dataset he created covered customer sales agreement information, which describes various aspects of the customer experience: their purchases within the company, frequencies, billing, customer balances as well as all the attributes about the products purchased. Given the large amount of data the team was utilizing, they were thrilled at the speed at which they could operate and process their data with Jedox.

The key objective for the Terminix team was to utilize AI for predicting and analyzing customer loyalty. Data was loaded into Jedox for processing by the AI engine. This allowed for a comparison of the AI prediction for customer loyalty to actual loyalty. “One of the first benefits was how quickly we were able to obtain results,” explained Cousin. “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. This included factors such as contract value, tenure, product mix, and whether the customer came to us, or we proactively reached out to that customer. We were just so focused on thinking that everything was service-related that we hadn’t taken many of these other features into consideration. The AI project sheds light on new features that could be causing the issues,” concluded Cousin.

Kennedy is currently preparing to set up a control test to follow these customers into the branches and see how that plays out over time. “I think the way that we can analyze the contribution of the AI results is to create two groups of branches with a similar geographic and economic setup – one that uses the AI results and one that does not – and compare the two,” he explained. “We are already looking at many different aspects when it comes to customer loyalty, improving the customer experience, and increasing customer retention. Therefore, it is also important to show that any improvements in the branches actually stem from the AI information, and nothing else is skewing the picture,” said Kennedy.

“Jedox gives a clearer, easier path to get started with AI instead of having to work from the ground up and needing specialized data scientists or developers on your staff. We have the ability to feed a dataset to the Jedox AI engine and then the ‘magic’ happens accessing pre-built algorithms based on industry-standard AI libraries. With Jedox, the finance department gains a direct solution pathway to information that it could not access before,” concluded Kennedy.

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 perspective 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.

Jamie Cousin, FP&A Manager at Terminix (Read the full interview)