GWO-CNN: Trust and Intelligent Recommendation system based model to improve marketing strategies on e-commerce

• Published in: 2024 IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE) pp. 648 - 652
• Main Authors: Sethi, Vikas, Kumar, Rajneesh, Mehla, Stuti
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.02.2024
• Subjects: Convolution; Convolution Neural Network (CNN); Data models; Employment; Entrepreneurship; Feature extraction; Feature Matrix; Filtering algorithms; Grey Wolf Optimizer (GWO); Machine Learning; Neural networks; Recommendation system
• DOI: 10.1109/ICWITE59797.2024.10503491

In 21 st century, AI-based intelligent recommendation system uses rating predictions, which are frequently utilized and helps users swiftly filter down their options and make informed judgements from an abundance of material. Nevertheless, as recommender systems only contain a small number of explicit data and are subject to cold start and sparsity issues, the majority of existing recommendation models have poor accuracy. The majority of conventional algorithms used to make recommendations simply take into account the straight-forward connection among consumers and products, largely ignoring the interests, prospective employment factors, or other social aspects of the products being recommended.In this study focus is on user preferences, as they are key to tailoring recommendations to individual needs. By combining trust values with user preferences, the system can recommend items that not only have a high trust value but also align with a user's individual tastes or needs. For this proposed model used feature matrix, Grey Wolf Optimizer (GWO) and Convolution Neural Network (CNN). GWO is an optimization algorithm used to find optimal weights or parameters for the recommendation system. Once the GWO has found optimal or near-optimal weights, they are integrated into the feature matrix. These weights can help prioritize or scale certain features to improve the recommendation quality. Then CNN will extract patterns and relationships from the feature matrix. Based on the processed feature matrix, the system predicts the top 'K' items to recommend to the user.