• Rajeshwari Kodulkar
• Dhanashri Kulkarni

Many researchers are interested in creating explicit feedback-based recommendation systems because there is a sizable quantity of explicit input, such as searching and tapping. Despite being overly challenging, explicit feedback is particularly appropriate while developing recommendation techniques. The learning potential of traditional collective filtering methods like matrix decomposition is constrained when user preferences are viewed as a linear mix of user and object latent attributes. They thus struggle with data sparsity and cold beginnings. In this project, deep neural networks will be used in addition to traditional collaborative filtering to map user and object attributes. On the other hand, scalability and data availability affect the effectiveness of the methodologies and limit the applicability of the proposals' findings. The authors then suggested combining user and item functions using the multi-model deep learning (MMDL) method to produce a hybrid RS that greatly improved. A one-dimensional neural network convolutional model which learns user and object properties is combined with a deep autoencoder in the MMDL technique to predict users’ expectations. The proposed study suggests considerable success in contrast to current methods based on an in-depth analysis of three models that produce a wide range of outcomes from a single real-world dataset.

"Deep Learning Approach with Multiple Models for Collaborative Filtering Recommendation System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 12, page no.b758-b769, December-2022, Available :http://www.jetir.org/papers/JETIR2212184.pdf

"Deep Learning Approach with Multiple Models for Collaborative Filtering Recommendation System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 12, page no. ppb758-b769, December-2022, Available at : http://www.jetir.org/papers/JETIR2212184.pdf