Problem
An online, direct-to-consumer retailer aimed to leverage the power of Artificial Intelligence/Machine Learning to boost Customer Lifetime Value (CLTV) through relevant, customer-specific product recommendations.
Solution Details
E-commerce Customer Acquisition Costs (CAC) have generally been trending upwards in the previous 2-3 years, driven by numerous factors including privacy challenges related to ad tracking, increased competition, and shifting consumer behavior.
When you pair these challenges with a diminishing Return on Ad Spend (ROAS) as marketing budgets increase, it becomes apparent that Customer Lifetime Value (CLTV) is just as critical a focus area as Customer Acquisition Cost (CAC).
One crucial tool to increase CLTV is providing accurate and timely product recommendations to enhance buyer engagement. In a sales model that typically includes multiple line items and frequent reordering, it is possible to tap into the power of Artificial Intelligence/Machine Learning to form a holistic picture of customer behavior and preferences.
The Toro Async team successfully paired a machine learning model with client-driven recommendation rules to develop a comprehensive solution. This solution provided existing customers with up-to-date product recommendations that combined a particular user’s buying behavior with site-wide customer order metrics and internal business rules.
The generated recommendations were seamlessly integrated into both the customer website and the customer’s email flows, enabling targeted recommendations and offers to reach the right customer at the right time.
Outcome
The custom Toro recommendations engine delivered a significant improvement to targeted metrics in a highly-competitive niche. 19% of customers selected their recommended products without modification when placing a repeat order. Customer Lifetime Value increased by 16% within 12 months of implementation.
