LANCER: A Lifetime-Aware News Recommender System

From the observation that users reading news tend to not click outdated news, we propose notion of 'lifetime' with two hypotheses: (i) has a shorter lifetime, compared other types items such as movies or e-commerce products; (ii) only competes whose lifetimes have ended, and which an overlapping lifetime (i.e., limited competitions). By further developing characteristics then present novel approach for recommendation, namely, Lifetime-Aware News reCommEndeR System (LANCER) carefully exploits during training recommendation. Using real-world datasets (e.g., Adressa MIND), successfully demonstrate state-of-the-art recommendation models can get significantly benefited by integrating LANCER, up about 40% increases in accuracy.