Optimizing Campaign Effectiveness: Identifying Target Customers via Recommender Engine

Authors: Nikita Katyal, Shubham Jain

Abstract:

In today’s competitive business environment, the success of campaigns relies not only on their creation but also on effectively reaching the right customers. Campaigns often feature products that customers may not have considered or are unaware of, including popular items. This research aims to enhance retailer sales by leveraging an efficient recommender system that reminds targeted customers to purchase their preferred products and suggests additional items they hadn’t initially considered during a campaign. Our focus is on utilizing the recommender system to identify potential customers for a curated set of products selected by the marketing team for a specific campaign. Communicating with all customers can be time-consuming and costly, and irrelevant messages may harm customer loyalty. Therefore, the primary objective is to strategically select the right customers for a campaign, increasing sales and reducing communication costs. This paper provides valuable insights into connecting with the right customer segments to optimize revenue generation for businesses. The analysis shows that high-value customers (those generating the highest revenue) contributed to increases in average basket size, while win-back customers (with low engagement) and about to churn customers (those at risk of attrition) improved the effectiveness of marketing contacts by increasing engagement and reducing churn. Targeted communication, focused on revenue, also enhanced the quality of the relationship between the customer and the firm, helping to lower churn rates by engaging customers with suitable campaigns. This research provides empirical evidence supporting the theoretical benefits of targeting the right customers for a campaign.

Keywords: recommendation, ALS, marketing campaigns, target customers, churn