This research aims to develop a more accurate and relevant content-based film recommendation system from the Netflix and Disney+ streaming platforms using the ANN method. Movie recommendation systems are a popular solution to help users find movies that match their preferences. The ANN method develops a model to learn complex patterns from film features. Additionally, Adam optimization is used to improve the speed and accuracy of the model training process. The advantage of using an ANN is its ability to learn complex patterns and improve the performance of the recommendation system over time. Adam Optimization helps improve the speed, accuracy and quality of ANN models. From this research, researchers, based on the evaluation results using the confusion matrix, obtained an accuracy value of 88.30%, using a split ratio of 80:20 and a learning rate of 0.04469992592930794. This means that most classifications can detect correctly according to sufficient data. Combining these two methods allows the film recommendation system to provide better recommendations as more data becomes available.
Keywords: Recommender System, Film, Content-Based, ANN, Adam.