A New Framework for Online Recommendation Systems Based on Open Approach Feedback

The vastly growing amount of information spread on the internet on a daily basis has created a challenging process of decision making to the users in many aspects. The available options of everything requires an active procedure of filtering and prioritizing to make it easier for the users to make the right choices. The idea of Recommender systems is that it studies the behavior of users and their preferences and provide them with the most suitable option available based on personalized generation. The proposed framework discusses generating an interactive experience between the users and some inanimate websites by analyzing their buying behavior and their characteristics and takes away the effort needed from the users. Feedbacker is a proposed solution for providing the users with recommendations that best suit their preferences and needs. This research has achieved promising results comparing with other applications in terms of its impact on service quality and its impact on customer behavior. Based on the explicit user input regarding their interests in the Feedbacker service and based on the collected data in studying customers’ behaviors, it has been found that the system serves as a compass for researches and practices in the field of recommendation systems. It has approximately achieved 80% of the feedback process success and approximately 60% in terms of CRM success.