949. Using Sensor Technology to Evaluate the Effects of a Price Promotion on Store Arrival Times
Invited abstract in session TD-47: Consumer Demand and Marketing I, stream Retail Operations.
Tuesday, 14:30-16:00Room: Parkinson B08
Authors (first author is the speaker)
| 1. | Ignacio Inostroza-Quezada
|
| School of Business and Economics, Universidad de los Andes | |
| 2. | Leonardo Epstein
|
| School of Business and Economics, Universidad de los Andes | |
| 3. | Ronald Goodstein
|
| McDonough School of Business, Georgetown University |
Abstract
Store managers conduct frequently marketing actions (MAs) to boost store traffic. Thus, measuring this traffic is crucial for assessing the effectiveness of such initiatives. Recently, store managers have gained access to sensors that record data continuously, enabling a more in-depth analysis of how their actions affect consumer behavior. In this talk, we present a novel approach that uses shopper-specific arrival times outside a MA to build a counterfactual baseline for store traffic during this MA. This baseline (i) assumes that the MA has not taken place, and (ii) is essential because a store cannot operate simultaneously with and without the MA. Next, we compare observed traffic data with the counterfactual baseline during the MA to evaluate its effect on store traffic. Finally, we assess the uncertainty of this effect during the MA. We illustrate our approach with data from an actual two-week price promotion, which showed an increase of 2880 store arrivals attributed to the promotion. Additionally, we complement our results with visual plots that help managers (i) examine the evolving effects of the promotion and (ii) understand the influence of time-varying covariates on consumer behavior.
Keywords
- Analytics and Data Science
- Forecasting
- Marketing
Status: accepted
Back to the list of papers