Retail Analytics

Designing Salesforce Compensation Schemes to Reduce Product Expiration

1–2% of the gross sales in the consumer-packaged-goods industry is typically wasted due to product expiration. Given the scale of the industry this amounts to about $15 billion per year. While there are many reasons for the product expiration one plausible reason is the often misaligned incentives between the sales-representatives and the manufacturer. In this paper we estimate the representative’s decision making process, and the factors that encourage or discourage sales, from the sales decisions data collected from a large consumer-packaged-goods manufacturer. Using this learnt model of the representatives’ behavior we construct manufacturer’s profit maximizing compensation schemes for different products and markets. We find that there are a significant number of cases where it is possible to both increase manufacturer’s profit and reduce the product waste from expiration by designing appropriate compensation structure for the sales-representatives in these markets. (SSRN)

with: Arzum Akkas

Discovering the Predominant Paths-to-purchase

The idea of path-to-purchase is often discussed in Research and Practice. We develop a method to identify the most common paths-to-purchase using multi-variate time-series datasets collected from CRM systems. The proposed approach involves using a generalized Vector Auto-Regression model to capture consumers’ movement from one activity to another (steps of the path), and at the same time identifying groups of consumers who have similar paths.

The proposed approach is evaluated on a large customer touch point dataset made available by the Wharton Customer Analytics Initiative. The multi-time period paths show distinct shopping behavior of customers in different groups. The value of knowing such paths is illustrated through an example application of targeted catalog mailing. (SSRN)

with : Yicheng Song, Shuba Srinivasan, Chris Dellarocas

Effect of Online Artifacts and Activities on Product Returns

With all the information a retailer has about customer’s and the products, can it predict if a particular purchase will be returned? This questions leads us into a broader inquiry into factors that affect customer’s purchase and return decisions. We find that different types of online product reviews play significant roles in customer’s return decisions, as do the customers’ shopping activities before purchase. The findings have implications for managing online product information, and developing strategies for handling transactions and reverse-logistics based on an improved knowledge of which purchases are going to successful. (SSRN)

with : Chris Dellarocas, Shuba Srinivasan