The Value of Fit Information in Online Retail: Evidence from a Randomized Field Experiment

Santiago  Gallino; Antonio  Moreno

Article | Manufacturing & Service Operations Management | Fall 2018

The Value of Fit Information in Online Retail: Evidence from a Randomized Field Experiment

by Santiago Gallino and Antonio Moreno

Abstract

Online channels generate frictions when selling products with nondigital attributes, such as apparel. Customers may be reluctant to purchase products they have not been able to try on, and those customers who do purchase may return products when they do not fit as expected. Virtual fitting-room technologies provide information about how a product fits a particular customer and promise to mitigate some of the frictions the information gap generates in the retailers’ supply chains. By implementing a series of randomized field experiments, we study the value of virtual fit information in online retail. In our experiments, customers are randomly assigned to a treatment condition where virtual fit information is available or to a control condition where virtual fit information is not available. Our results show that offering virtual fit information increases conversion rates and order value and reduces fulfillment costs arising from returns and home try-on behavior, that is, customers ordering multiple sizes of the same product. We explore mechanisms through which providing virtual fit information helps customers and retailers. We argue that the virtual fitting tool creates spillovers even to products that are not available for virtual try-on, increases loyalty, helps customers better parse their choice sets, and reduces uncertainty by providing size recommendation.

Keywords: supply chain information; fit uncertainty; online retail; randomized field experiment; virtual fitting room; digital retail; Customization and Personalization; Online Technology; Value; Performance Improvement; Apparel and Accessories Industry; Retail Industry;

Format: Print

Find at Harvard

Citation:

Gallino, Santiago, and Antonio Moreno. "The Value of Fit Information in Online Retail: Evidence from a Randomized Field Experiment." Manufacturing & Service Operations Management 20, no. 4 (Fall 2018): 767–787.

The Indian banknote demonetization in 2016 was one of the most significant international events of that year. Overnight, 86% of Indian currency in circulation was declared invalid unless exchanged for new bills. The sudden and unexpected demonetization constituted a large shock to the entire Indian economy. One effect of the ensuing cash shortage was a large and sustained increase in the adoption and usage of digital payments. We use detailed sales data consisting of more than two and a half million transactions from a leading Indian online retailer to empirically investigate the effects of payment digitization on the online retail industry. We take advantage of the demonetization as a source of exogenous variation that induced a subset of consumers to switch to digital payments from more commonly used cash-on-delivery payments. We show that consumers who switch to digital payments maintain their purchase frequency but spend more and are less likely to return their purchases. Our findings show that firms in emerging markets may enjoy gains from consumer demand in addition to operational gains resulting from payment digitization.

Article | Production and Operations Management | October 2018

The Operational Value of Social Media Information

Ruomeng Cui, Santiago Gallino, Antonio Moreno and Dennis J. Zhang

While the value of using social media information has been established in multiple business contexts, the field of operations and supply chain management have not yet explored the possibilities it offers in improving firms' operational decisions. This study attempts to do that by empirically studying whether using publicly available social media information can improve the accuracy of daily sales forecasts. We collaborated with an online apparel retailer to assemble a dataset that combines (1) detailed internal operational information, including data on sales, advertising, and promotions, as well as (2) publicly available social media information obtained from Facebook. We implement a variety of machine learning methods to forecast daily sales. We find that using social media information results in statistically significant improvements in the out-of-sample accuracy of the forecasts, with relative improvements ranging from 12.85% to 23.23% over different forecast horizons. We also demonstrate that nonlinear boosting models with feature selection, such as random forests, perform significantly better than traditional linear models. The best-performing method (random forest) yields an out-of-sample mean absolute percentage error (MAPE) of 7.21% when not using social media information and 5.73% when using social media information is used. In both cases, this significantly improves the accuracy of the company's internal forecasts (a MAPE of 11.97%). Combining these empirical results, we provide recommendations for forecasting sales in general as well as with social media information.

Keywords: social media; Machine learning; Information; Sales; Forecasting and Prediction;

Citation:

Cui, Ruomeng, Santiago Gallino, Antonio Moreno, and Dennis J. Zhang. "The Operational Value of Social Media Information." Special Issue on Big Data in Supply Chain Management. Production and Operations Management 27, no. 10 (October 2018): 1749–1774. View Details

Cite View Details Find at Harvard Purchase

Faculty & Research

The Value of Fit Information in Online Retail: Evidence from a Randomized Field Experiment

Abstract

Citation:

About the Author

More from the Author