The Operational Value of Social Media Information

Ruomeng  Cui; Santiago  Gallino; Antonio  Moreno; Dennis J. Zhang

Article | Production and Operations Management | October 2018

The Operational Value of Social Media Information

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

Abstract

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;

Format: Print

Find at Harvard Purchase

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.

Spoilage, expiration, damage due to employee/customer handling, employee theft, and customer shoplifting usually are not reflected in inventory records. As a result, records often report phantom inventory, i.e., units of good not available for sale. We derive an optimal polynomial-time algorithm for the auditing and replenishment problem with phantom inventory, under the assumption that inventory is known immediately after replenishment. Moreover, we numerically show that a projected service-level threshold policy performs comparably to the optimal.

In 2010, amidst the growth of ecommerce and the emergence of new, purely online, fashion players, Zara launched its first online store, Zara.com. Since then, Zara’s online business had grown at a fast pace. By 2018, 12% of Inditex Group’s total sales came from the online channel. Since the inception of the first online store, Inditex leadership wanted its online and offline businesses to be integrated. However, the increase of online orders challenged some of its operations. Inditex was committed to the vision of becoming fully integrated, fully digital, and fully sustainable by 2020. How could stores continue to be relevant in a world with increasing presence of online touchpoints? What should the store portfolio look like in the medium term? How should Zara use and advance the integrated model going forward? What other challenges and opportunities would arise with the increase of online sales?

Faculty & Research

The Operational Value of Social Media Information

Abstract

Citation:

About the Author

More from the Author