Yücebaş, Sait Can2025-01-272025-01-2720192459-1580https://search.trdizin.gov.tr/tr/yayin/detay/380583https://hdl.handle.net/20.500.12428/19412The amount of data in World Wide Web is growing exponentially. Users are often lost inthis vast ocean of data. In order to filter the valuable information from vast amount of data,recommendation systems are used. These systems are based on collaborative filtering,content based filtering and hybrid approaches. We combined collaborative and contentbased filtering to build a hybrid movie recommendation system, MovieANN, based onneural network model. To make better recommendations in a collaborative approach, bothuser and movie clusters are formed. In addition to rating information, content informationwas also considered in the formation of the clusters. Clusters are formed according to KMeans and X-Means algorithms. Final clusters are chosen according to Davies-BouldinIndex and intra cluster distance. Homogeneity and density of the clusters are alsoconsidered. Movie and user clusters are mapped in the recommendation phase. The modelis tested on a MoiveLens 1M dataset that consists of six thousand users, four thousandmovies and one million ratings. Four clusters are formed to represent movie – usermappings and for each cluster, a recommendation model based on multi-layer neuralnetwork is constructed. The recommendation performance in terms of accuracy is 84.52%,84.54% in terms of precision and 99.98% in terms of recall.eninfo:eu-repo/semantics/openAccessBilgisayar BilimleriYazılım MühendisliğiBilgisayar BilimleriTeori ve MetotlarBilgisayar BilimleriYapay ZekaArticle52214232380583