... techniques to efficiently and accurately predict partially observed and unobserved results. Deep learning Recommendation system Matrix factorization Long short-term memory In this information explosion (i.e. info-plosion) era, owing to the exponential growth of information and data, how...

.../methodology/approach The authors proposed a novel learning-based method, the pattern-based dual learning POI recommendation system as a solution to consider users' interests and the uniformity of popular POI patterns when making recommendations. Differing from traditional long short-term memory (LSTM), a new...