Improving Recommendations Using Traceability and Machine Learning

The intelligent filtering systems known as Recommender systems, are important tools meant to assist users in their choices and solve the issue of information overload, as they can predict and provide suggestions, intended to meet users’ interests and expectations. For this purpose, the recommendation process uses different data which is extracted from the users’ preferences and interests (User Profile) and the items’ characteristics. These systems employ the same techniques but different approaches that exploit textual and history data from users’ activities, taken either from their profiles or from other valuable resources and are often combined to provide the most suitable results. However, due to the increasing volume of data, the recommendation becomes more redundant and the same elements get proposed repeatedly. In this paper, we intend to discuss the benefits of using traceability and machine learning and how they can improve the recommendation and make it more efficient and reliable.