According to a new study by researchers at Oregon State University, location-based data from social commerce websites can provide valuable insights for strategic and operational business decisions.
The study, published in the July issue of the journal Expert Systems With Applications, presents a framework of location-based business performance prediction.
Social commerce websites, such as Yelp, collect a lot useful information from its users, such as customer opinions, geographical distribution of businesses in a given area, and customer “check-ins”.
Lead author of the study, Xiaohui Chang, an assistant professor in OSU’s College of Business, says that this type of data can be useful for business owners wanting to know more about the competitive environment in which they operate or are considering operating in.
The researchers developed a tool which uses data collected through a social commerce site that can determine whether one location would be better for business than another. The framework of location-based business performance prediction takes into account both intrinsic and extrinsic factors.
“Small business owners, in particular, have a lot of choices when opening a new business, including where to locate,” Chang said. “With this model, we use existing social commerce data to help you determine which location is going to perform the best.”
The researchers tested the accuracy of four different business performance prediction models in predicting whether a restaurant would be successful: an attribute affinity model, a geographic model, a contextual model, and a hybrid model that uses both contextual and geographic models.
Each model was tested using Phoenix-area restaurant data from the social commerce site Yelp.
The team found that the hybrid model, which adopts both link-based and context-based assumptions, was the best model at predicting whether a restaurant would be successful.
Additional research is necessary, says Chang
Chang said that more research is necessary to test how the model could be used to help businesses and see if it also works for other types of businesses.
“You could regularly get new performance predictions and the data could be used to help businesses solve problems or keep themselves vibrant,” Chang said.
“If a similar business is more successful and you can use location-based data to pinpoint that the success is due in part to parking availability, hours or price point, you can make decisions based on that information.”
“Business performance prediction in location-based social commerce”
Expert Systems with Applications
Volume 126, 15 July 2019, Pages 112-123
Xiaohui Chang, Jiexun Li