Using online search data to forecast new product sales

Abstract

This dissertation focuses on online search as a measure of consumer interest. Internet use is at an all-time high in the United States, and according to the Pew Internet & American Life Project, 91% of Internet users use search engines to find information.Consumers' choices of search terms are not well understood. However, we argue that people will focus their searches on terms that are of interest to them. As such, data on the search terms used can provide valuable measures and indicators of consumer interest in a market. This can be particularly valuable to managers in search of tools to gauge potential product interest in a new product launch. In this research, we develop a model of pre-launch search activity. We find search term usage to follow rather predictable patterns in the pre-launch and post-launch periods. As such, we extend our pre-launch search model to link pre-release search behavior to releaseweek sales -providing a very valuable forecasting tool. We illustrate this approach in the context of motion pictures. Our modeling framework links search activity to sales and incorporates product characteristics. Our results indicate consistent patterns of search over time and systematic relationships between search volume, sales, and product attributes. We extend our model by studying the role of advertising. This allows us to better understand the relationship between advertising and online search activity and also allows us to compare the forecasting performances of each of the two approaches. We find that search data offers significant forecasting power in opening-weekend box-office revenues. We further find that advertising, combined with search data, offers improved forecasting ability.

Prerelease Buzz Evolution Patterns and New Product Performance

“…Prerelease buzz volume can explain and predict new product sales for the following reasons. 5 First, it reflects the amount of consumer interest and engagement in the product before its launch (Kulkarni et al 2012). High consumer interest in the prerelease period leads to eager anticipation (since the nonavailability of the product disrupts the goal of consumption), building up pent-up demand (Houston et al 2011).…”

“…Second, postrelease word of mouth can have an immediate impact on purchase; however, when a potential consumer is exposed to prerelease buzz about product X, the product is not yet available on the market, and thus the impact of this buzz cannot be realized into actual purchase behavior until product release. Previous research suggests that consumer search of the product information online over time before product release can also indicate consumer interest in the upcoming product (e.g., Houston et al 2011, Kulkarni et al 2012. Hence, we also model prerelease search in comparison with prerelease buzz.…”

“…The other study using prerelease time-series data,Kulkarni et al (2012), models the hazard (i.e., probability, instead of volume) of weekly online search over eight weeks before movie release but does not directly estimate the impact of prerelease search pattern on sales.4 The augmented Dickey-Fuller tests indeed suggest that the prerelease dynamics of most sample products are nonstationary.Downloaded from informs.org by[130.194.20.173] on 03 December 2014, at 23:16 . For personal use only, all rights reserved.Xiong and Bharadwaj: Prerelease Buzz Evolution Patterns and New Product Performance…”

A survey on retail sales forecasting and prediction in fashion markets

“…They report higher correlation between movie revenues and online activity in contrast to search queries related to songs. Similarly, Kulkarni, Kannan, and Moe (2012) consider search volume as product interest and a significant indicator for future box-office revenues. Eysenbach (2006) even (2011) Epidemiology User-generated content Asur and Huberman (2010) Box office revenues User-generated content Bermingham and Smeaton (2011) Elections User-generated content Bollen et al (2011) Stock market User-generated content Boulos et al (2010) Health/surveillance Search queries Choi and Varian (2012) names search engine queries demand in order to emphasize the relevance of these keywords.…”

Contribution of Food Commercials' Informational/Emotional Appeals to Japanese Consumer Attitude and Purchase Intention

“…It is especially necessary to choose a new food product to decrease the influence of familiarity. Consumer information search is likely to take place, and informational appeals for a new product are expected to play an important role in purchase intention [19]. Consequently, we tailored, designed, and shot eight samples of commercials for plant factory products.…”