Businesses with physical footprints – hotels, retailers, and restaurants – must identify the competitors that matter most. Traditional approaches using brand tier or proximity often fail in dynamic or asymmetric markets. We introduce the Conditional Sure Independence Screening (CSIS) method to marketing to identify true competitors based on their pricing influence on a focal firm’s demand. CSIS is computationally efficient, robust to spatial mis-specifications, and effective for identifying, asymmetric, even non-local, and segment-specific competition. It is also an effective variable selection technique.
In applying CSIS to U.S. hotel data our analysis shows that competition intensity varies not only by location or market segments, but that asymmetry is common – many hotels influence others without being influenced in return. Our methodology enables smarter, data-driven pricing and benchmarking and helps tailor strategy to segment and seasonality. In addition, it is scalable across industries such as retail, services, and hospitality.
Xian Gu, Assistant Professor, Kelley School of Business, Indiana University; P.K. Kannan, Dean's Chair in Marketing Science, Smith School of Business, University of Maryland
Journal of Marketing Research