Recommender system is an encouraging technology for enterprises to present personalized suggestions to their customers. But this technology suffers from sparsity problem. In addition, greatest researches are grounded on explicit rating. But most users do not spend time for rating of products. Therefore, this research proposes an effective recommendation based on user behavior Consumer behavior is one of the most important issues that have been discussed in recent decades. Organizations always want to understand how consumer makes decisions so that they can use it to design their products and services. Having a correct understanding of the consumers and the consumption process has many advantages. These advantages include helping managers make decisions, providing a cognitive basis through consumer analysis, helping legislators and regulators legislate on the purchase and sale of goods and services, and ultimately helping consumers make better decisions. Here is a solution for recommending goods based on the users' past behavior over deep learning. The architecture expressed for deep learning is trained by users' past behavioral data. Amazon data was studied and the results indicated that the proposed method has a much higher accuracy than similar methods. Primary contribution is implementation of a user behavior-based recommendation method that discovers interest of users based on implicit rating of product attributes. In addition, this approach uses sequential pattern of purchasing to improve the quality of recommendation.
展开▼
