Reports

Leveraging the Power of Images in Predicting Product Return Rates

Daria Dzyabura, Siham El Kihal, and Marat Ibragimov, 2018, 18-135-10

Product returns generate huge costs for online retailers. Data show that the average product return rate per item is 53% online but only 3% offline, for the same set of products. Processing and refurbishing returned items is costly and return costs range between $6 and $20 per returned item. Thus, even small changes in return rates can result in large profit improvements.

In this report, Daria Dzyabura, Siham El Kihal, and Marat Ibragimov demonstrate how a firm can incorporate visual features extracted from product images into a prediction model of return rates prior to a product’s launch.

Study

Their analysis is based on a large data set from a European apparel manufacturer and retailer, which includes over 1.8 million online and offline transactions over four years involving near 10,000 unique fashion products. They use a machine learning approach that combines several image feature extraction tools to quantify information from images, and a gradient boosted regression tree prediction model.

Among their findings:

First, consumers’ demand for products differs online and offline, such that some products attain higher market shares online than offline or vice versa. Furthermore, controlling for online demand, products with lower offline demand have higher online return rates. This relationship is not simply due to missing information on the touch-and-feel attributes of the product online.

Second, it is possible to predict return rates with high accuracy based on a product’s online description: price, category, and product image. Incorporating the visual features of a product considerably improves the accuracy with which the model can predict return rates by 37% compared to models using only non-image characteristics.

Put into Practice

Retail managers can use this approach to better forecast an individual product’s profitability and make effective merchandising and retailing decisions. Omnichannel retailers may be able to launch products earlier in offline channels, and due to their ability to more accurately predict return rates, make informed decisions about launching products online. In addition, incorporating product images can be applied to other key economic variables in addition to a product’s return rate, such as clicks, demand, or even consumer search models.

Daria Dzyabura is Associate Professor at the New Economic School, Moscow. Siham El Kihal is Assistant Professor of Marketing at Frankfurt School of Finance & Management. Marat Ibragimov is a Ph.D. candidate at MIT Sloan School of Management.

Related links

Making Words Speak: Leveraging Consumer Insights from Online Review Text to Improve Service Quality
Andrea Ordanini, Raji Srinivasan, and Anastasia Nanni (2018) [Report]

Large-Scale Cross-Category Analysis of Consumer Review Content on Sales Conversion Leveraging Deep Learning
Xiao Liu, Dokyun Lee, and Kannan Srinivasan (2018) [Report]

Pricing:

  • Corporate: FREE
  • Academic: FREE
  • Subscribers: FREE
  • Public: $18.00

3 WAYS to GET CONNECTED

Business

Employees of MSI Member Companies enjoy the benefits of complete online access to content, member conferences and networking with the MSI community.

More

Academic

Qualified academics benefit from a relationship with MSI through access to msi.org, conferences and research opportunities.

More

Public

The public is invited to enjoy partial access to msi.org content, a free e-newsletter, selected reports and more.

More

Featured:

Become a Subscriber

MSI's Online Library of 400+ reports, authored by marketing academics, offers new research and evidence-based insights

Read More

Priority Topics

Stay Informed

The MSI Mailing List

Subscribe to our email list to stay informed about upcoming events, news, etc.

Social Media