Can Online Consumer Reviews Signal Restaurant Closure: A Deep Learning-Based Time-Series Analysis

Abstract

Business closure is a critical stage in the lifecycle of any business. Despite a body of literature on the factors influencing business failure and/or success, studies on business closure prediction are next to none. Additionally, the identification of those factors has focused primarily on the managerial and economic dimensions rather than the consumer dimension. This research investigates the prediction of business closure from online consumer reviews, and validates the predictive models in the restaurant industry, which is subject to a relatively high attrition rate. Our proposed method for predicting business closure includes several novel artifacts, including integrating deep learning and time-series analysis techniques, extracting information embedded in online reviews using a hybrid classification method, and incorporating a novel triple word embedding model for text representation. The evaluation results of the proposed method using Yelp online reviews demonstrate its superior performance in business closure prediction, which indicate that online reviews provide strong signals for predicting business closure. We conduct another experiment with review data collected from TripAdvisors.com, and the experiment results are consistent, which provide evidence for the generalizability of the proposed method. The findings of this research have important managerial implications for business and investment decision making.