Alvin Electronics Leverages Machine Learning to Predict and Manage Customer Churn
With over 30 years’ experience in TV antennas, cables, connectors and audio/visual equipment, Alvin Electronics has efficiently serviced the needs of Australia’s data and security trade industries.
Working out of a trade store environment, Alvin Electronics has built a strong business over the years, with a relatively small sales and marketing team. The team supports over 1,800 customers who have often presented numerous challenges in maintaining an efficient and proactive spread of service and support to them all.
Alvin Electronics approached Spyglaz with a view to creating a better way to improve their customer retention efforts.
Learning From Your Historical Customer Data
The Spyglaz team worked with the team at Alvin Electronics to understand customer purchasing cycles and behaviors. Spyglaz also assisted with the extraction of sales data from the Alvin point of sale system and quickly extracted two years’ of transactional data across their entire customer base.
Spyglaz then used their proprietary machine learning algorithms to analyze and identify trends that had historically led to customer loss. The algorithms used this learning to deliver predictions on which customers Alvin Electronics were most likely to lose in the future.
All customers were assigned a churn probability score and sorted by sales value, which made it easy for the sales team to approach the highest value, at-risk customers first.
The process of leveraging machine learning to analyze customer data and predict future business outcomes delivered key new insights, some of which came as a surprise to the management team.
“I thought I knew my business well, but Spyglaz taught me things about my business that I didn’t know,” said Stephen Hanlon, Managing Director at Alvin Electronics.
How Predictive Analytics Can Help Reduce Customer Churn
Stephen and the team decided to act on these insights and embarked on a focused program of reducing customer churn, targeting the customers most likely to leave, as identified through Spyglaz. The sales team reconnected with these at-risk customers with calls, emails and pitches to renew contracts.
This sustained program of customer outreach resulted in an improvement of “customer engagement and retention by 70%”. Of all customers contacted from the Spyglaz list of potential churn predictions, 70% either placed repeat orders or agreed to a follow-up sales call.
Alvin Electronics are now running their data through Spyglaz on a regular basis to maintain their focus on customer retention and getting repeat business from their existing customer base. Monthly insights reporting from Spyglaz has enabled them to get a quick read on progress they are making with reducing overall customer churn.
To learn more about how Spyglaz can help you, please email us at firstname.lastname@example.org.