• Ritika Varpe
• Seema Patil

This report conducts research on movie recommendation systems using deep learning concepts. Which movies are best depends upon how they have received the ratings. By classifying and predicting the ratings given by the user which movie should be recommended to the user is decided. It has classified the ratings according to the unique users and the unique movies. A traditional method for recommendation systems is used, matrix factorization. The summary has been driven by matrix factorization and a neural collaborative filtering model. It gives input, different layers, and output. Deep learning has great success in various areas such as segmentation, image classification, speech and text recognition, facial expression recognition, etc. A small comparison between matrix factorization and neural collaborative filtering is made which gives a brief idea about a recommendation system. To suggest two different methods to use of the neural network that is collaborative filtering and matrix factorization where the concatenation of user and item embedding is performed. The machine learning algorithm that is mean absolute error has been used for the prediction of the models. After this, the model uses the evaluation matrix for calculating the predictions received by the model. The recommendation system has its evaluation matrix such as Discounted Cumulative Gain(DCG) and Normalized Discounted Cumulative Gain(NDCG) which has helped to give accurate predictions. Additionally, the report explores the limitations and challenges in applying recommendation systems along with serval avenues for future research.

Recommendation System, Deep Neural Network, Matrix factorization, Neural collaborative filtering, Embedding.

"Neural Collaborative Filtering For Movie ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p262-p265, April-2024, Available :http://www.jetir.org/papers/JETIR2404G33.pdf

"Neural Collaborative Filtering For Movie ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp262-p265, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G33.pdf