Location selection is a crucial decision that must be made in the
restaurant industry. Conventional statistical approaches that
address the location selection problem are associated with theoretical
limitations that might lead to ineffective and misleading
inferences. This study proposed a data mining framework based on
RST to extract potentially useful rules from location data. The
proposed methodwas illustrated and its validity was demonstrated
using a case study of a restaurant chain. RST was applied to predict
store performance with location factors. Eschewing the need for
the assumptions required by the regression model, a number of
simple and understandable rules were derived to support location
selection decisions. From the analysis results, the most significant
location factors that affect store performance are “store size,”
“availability of parking area”, “store visibility”, and “population
growth rate of the vicinity”. Therefore, management teams should
pay more attention to these four factors when they survey locations