Café and Restaurant under My Home: Predicting Urban Commercialization through Machine Learning

The small commercial stores opening in housing structures Seoul have been soaring since the beginning of this century. While commercialization generally increases urban vitality and achieves land use mix, cafés restaurants low-rise residential areas may attract numerous passenger populations, with increased noise crimes, area. is so fast prevalent that neither researchers nor policymakers can respond to it timely without a practical prediction tool. Focusing on restaurants, we propose an XGBoost machine learning model predict store openings further play role early warning system. Our findings highlight large degree difference predictor importance between variables used our model. most important relates price, indicating economic motivation leads conversion restaurants. Mapo neighborhood predicted be prone housing, therefore, its urgency prepared against expected deserves underscoring. Overall, results show approach applied changes uses contribute policy designs rapidly changing context.