Optimizing Item-based Marketing Promotion Efficiency in C2C Marketplace with Dynamic Sequential Coupon Allocation Framework

TL;DR

The paper tackles the challenge of promoting transactions in C2C marketplaces from the seller perspective, where existing strategies often optimize promotions in isolation and ignore long-term continuity. It introduces Dynamic Sequential Coupon Allocation Framework (DSCAF), a two-predictor (both based on S-learner for CATE) approach that estimates sale propensity for current and subsequent rounds, trained with RCT data for the first round and unsold-item data for the second, and uses Inverse Propensity Weighting to reduce selection bias. By computing a combined propensity $p_{ijk}$ and ROI $ROI_{ijk}$, DSCAF selects sequential coupon configurations that maximize ROI while keeping lift above a threshold, effectively balancing costs and expected sales. Empirical results on a large Mercari dataset demonstrate substantial ROI gains and provide insights on optimal timing and coupon lifetimes, enabling scalable, long-horizon optimization for seller satisfaction and platform efficiency.

Abstract

In e-commerce platforms, coupons play a crucial role in boosting transactions. In the customer-to-customer (C2C) marketplace, ensuring the satisfaction of both buyers and sellers is essential. While buyer-focused marketing strategies often receive more attention, addressing the needs of sellers is equally important. Additionally, the existing strategies tend to optimize each promotion independently, resulting in a lack of continuity between promotions and unnecessary costs in the pursuit of short-term impact within each promotion period. We introduce a Dynamic Sequential Coupon Allocation Framework (DSCAF) to optimize item coupon allocation strategies across a series of promotions. DSCAF provides sequential recommendations for coupon configurations and timing to target items. In cases where initial suggestions do not lead to sales, it dynamically adjusts the strategy and offers subsequent solutions. It integrates two predictors for estimating the sale propensity in the current and subsequent rounds of coupon allocation, and a decision-making process to determine the coupon allocation solution. It runs iteratively until the item is sold. The goal of the framework is to maximize Return on Investment (ROI) while ensuring lift Sell-through Rate (STR) remains above a specified threshold. DSCAF aims to optimize sequential coupon efficiency with a long-term perspective rather than solely focusing on the lift achieved in each individual promotion. It has been applied for item coupon allocation in Mercari.

Figures (4)

• Figure 1: Item Coupon Display on Mercari. A discount badge is displayed when an item coupon is attached.
• Figure 2: Dynamic Sequential Coupon Allocation Framework (DSCAF).
• Figure 3: (a) STR with varying time delays following key actions. X-axis displays different hourly delay slots for coupon attachments; (b) Hourly STR of a two-hour delay distribution. X-axis is the transaction timing. Y-axis represents STR.
• Figure 4: (a) AOV trends over hours after attaching item coupons; (b) Model performance evaluated by cumulative uplift with Bootstrap Sampling.