Predicting Online Purchase Conversion for Retargeting

TLDR

Generally only about 2 % of shoppers purchase on their first visit while the remaining 98 % merely browse; retargeting is a crucial strategy to bring these window‑shoppers back and convert them into buyers. The study aims to estimate product‑specific conversion rates for existing customers, a key metric for retargeting. We jointly model customer‑ and product‑level conversion patterns using a buying‑decision framework and evaluate it on a simulated dataset derived from real‑world web logs. Our approach yields consistently more accurate and robust conversion predictions than existing baselines in dynamic market settings.

Abstract

Generally 2% of shoppers make a purchase on the first visit to an online store while the other 98% enjoys only window-shopping. To bring people back to the store and close the deal, "retargeting" has been a vital online advertising strategy that leads to "conversion" of window-shoppers into buyers. As such retargeting is more effective as a focused tool, in this paper, we study the problem of identifying a conversion rate for a given product and its current customers, which is an important analytics metric for retargeting process. Compared to existing approaches using either of customer- or product-level conversion pattern, we propose a joint modeling of both level patterns based on the well-studied buying decision process. To evaluate the effectiveness of our method, we perform extensive experiments on the simulated dataset generated based on a set of real-world web logs. The evaluation results show that conversion predictions by our approach are consistently more accurate and robust than those by existing baselines in dynamic market environment.