Spatio-temporal adaptive fusion transformer for next POI recommendation

• This study is the first to use Random Fourier Features (RFF) as a kernel-approximation technique. • It builds a Learnable RFF in the model capturing complex spatial relationships transforming input data into a higher dimensional feature space. • It focuses on both categorical and temporal dependencies along with spatial relationships that helps capture user preferences better. • Extensive analysis is conducted to decisively evaluate the effectiveness of the proposed model using two publicly available datasets that feature real check-in histories from Location-Based Social Network (LBSN) users. • The results demonstrate that the proposed technique outperforms leading baseline models, showcasing its superiority and distinct advantages. The rapid proliferation of smartphones and location-based services has accelerated the development of intelligent systems in various fields, such as tourism, ride-sharing, delivery and shipping services, user engagement, etc. In this context, next Point of Interest (POI) recommendation plays a vital role in predicting where a user will go based on their visit sequences or check-in histories. Recent advances in sequential modeling have led to more accurate recommendations; however, capturing complex interactions across spatial, temporal, and categorical dimensions remains challenging. They are important because they affect users' desire to visit a place at a certain moment. Many current models are inadequate because they either ignore the important influence of POI categories, reduce spatial coordinates to broad region IDs, or conduct temporal analysis exclusively using recurrent neural networks. This paper presents an innovative deep-learning framework Spatio-Temporal Adaptive Fusion Transformer (STAFT), systematically addressing these challenges by seamlessly integrating continuous spatial encoding, category-aware context weighting, and learning sequential pattern. Our model employs Learnable Random Fourier Features (RFF) to transform raw spatial features into richer, high-dimensional embeddings. It also emphasizes relevant POI categories utilizing Category Aware Attention and a Temporal Convolutional Network (TCN) to efficiently capture local temporal dependencies. The Transformer Encoder architecture is used at the core to produce the final prediction. Empirical results from experimentation on real-world datasets demonstrate that our approach performs better than existing models by 4-9% on commonly used metrics.