Multi-slot memory with dynamic gating: A multi-task framework for interpretable sequential recommendation in niche POI scenarios

Sequential point-of-interest (POI) recommendations in niche cultural-tourism settings must capture users’ parallel interests and rapid intent shifts.

Therefore, an Osaka Metropolitan University research team conducted a study that proposes a transparent multi-task framework that combines a multi-slot user memory with a dynamic gating network to jointly predict the next POI and the next thematic intent. User histories are divided into interpretable slots, such as travel themes or railway lines, and an encoder state at each step is compared with these slots to identify the most relevant one. The gate’s weights indicate which preference slot drives each prediction, providing step-level explanations.

Experiments on a real-world dataset of Japanese railway-stamp rallies demonstrate consistent improvements of 1.5–4.0 percentage points in Precision@5, NDCG@5, and theme-classification accuracy over strong baselines including GRU4Rec, SASRec, and single-slot memory models. Ablation analysis confirms that both the multi-slot memory and the gating mechanism contribute to performance gains. Visualization of gating patterns further reveals meaningful intent transitions, offering human-readable transparency valuable for cultural-tourism applications. The findings highlight the importance of interpretable memory and multi-task learning for accurate and explainable recommendations in specialized POI environments. 

### 

About OMU 

Established in Osaka as one of the largest public universities in Japan, Osaka Metropolitan University is committed to shaping the future of society through “Convergence of Knowledge” and the promotion of world-class research. For more research news, visit https://www.omu.ac.jp/en/ and follow us on social media: X, Facebook, Instagram, LinkedIn.