Personalized hybrid book recommender system using neural network

Recommender systems play a significant role in e-commerce industry. They provide personalized recommendation to each user. In this paper we present an approach in which we use customer's demographic information such as sex, age and geographical location as well as book information such as title and ISBN number to predict rating of books within range of 1 to 5 using a MLP-Neural Network. The customer location can be obtained through customer's IP address which further converted into a unique IP number. We also consider user's gender for recommendation process by assigning different value to sexual categories. Parameters such as gender, age and location enhance personalization factor in the recommendation process. Books can be recommended to a user by assuming suitable threshold rating. Our approach accepts challenges of recommender system and provides innovative solution to these challenges. We evaluate present approach in Matlab.