• Patel Prakrutiben Jitendrakumar
• Abhishek Devendrakumar Patel

Product recommendation is a technique that is being applied to most of the eCommerce platforms and for different businesses to analyze buyer’s behavior periodically. Unsupervised Learning finds a natural fit with unlabeled data. This leads to efficient principal component analysis and in such way we can understand the data and its properties. Moving beyond the age-old techniques, if we use latest machine learning with deep learning algorithms, we are able to calculate right products and the high-dimensional space based recommendation techniques. This enables us to use different clustering and classification methods, such as k-means and k-medians and hierarchical clustering and SVM, NB and random forest classification. We also use Shannon entropy and mean squared error to find optima. If the input data are labelled, then an exponential speedup is feasible over classical algorithms with the proposed algorithm, which is capable of their self-analysis for better results.

Recommendation System, LDA, Factorization, NN Classifier

"A Novel Product Recommendation Approach with Modified Self-Attention Mechanism and Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.1038-1044, April-2020, Available :http://www.jetir.org/papers/JETIR2004141.pdf

"A Novel Product Recommendation Approach with Modified Self-Attention Mechanism and Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp1038-1044, April-2020, Available at : http://www.jetir.org/papers/JETIR2004141.pdf