Embracing LLMs for Point-of-Interest Recommendations

A point-of-interest (POI) recommendation becomes the core function of location-based services. Unlike a traditional item recommendation, a POI recommendation has distinct features, such as geographical influences, complex mobility patterns, and a balance between local and global user preferences. Past POI recommendation system research has focused mainly on integrating deep learning models like convolutional neural networks, recurrent neural networks, and attention-based architectures, demonstrating their effectiveness in addressing the dynamic nature of spatial-temporal data in POI recommendation areas. In recent years, with the rise of large language models (LLMs), POI recommendation has produced a number of promising directions. This article first discusses the characteristics and state-of-the-art solutions of POI recommendation, then it introduces potential research directions by integrating the latest LLMs.