Can Google Trends Improve Your Sales Forecast?

• 成果类型: Article
• 署名作者: Boone, Tonya; Ganeshan, Ram; Hicks, Robert L.; Sanders, Nada R.
• 署名单位: William & Mary; William & Mary; Northeastern University
• 刊物名称: PRODUCTION AND OPERATIONS MANAGEMENT
• ISSN/ISSBN: 1059-1478
• DOI: 10.1111/poms.12839
• 发表日期: 2018
• 页码: 1770-1774
• 关键词: Forecasting; search queries; big data

摘要

In this issue, Cui etal. () show how the quantity and quality of user-generated Facebook data can be used to enhance product forecasts. The intent of this note is to show how another type of user-generated contentcustomer search data, specifically one obtained from Google Trendscan be used to reduce out-of-sample forecast errors. Based on our work with an online retailer, we bolster Cui etal. () result by showing that adding customer search data to time series models improves out-of-sample forecast errors.