Movie Recommendation based on User Similarity of Consumption Pattern Change

The recurrent neural network(RNN) deep learning algorithm, which mainly learns and predicts sequence data and time series data, is mainly used in language modeling, stock price prediction, and chat bot. In this paper, we propose a method of predicting and recommending a movie by considering movie consumption patterns of users. We measure the similarity between users based on movie rating data, classify users with similar movie preferences, and learn the consumption pattern of each similar user group to improve the prediction accuracy by considering the change of preference over time. In order to show the effectiveness of the proposed method, we apply the collaborative filtering algorithm, the simple RNN and our modified RNN and compare their prediction accuracies.