Abstract:
Recommender systems are very useful in assisting users to make profitable decisions. The process of making decisions on housing choices can be overwhelming and confusing for users given a large number of choices available to review while searching online. Over the years, different recommender systems have appeared, with collaborative-filtering systems and content-based systems being the most widely used, but none of these have been found to be effective for items that are not purchased often. This is because they require previous ratings which may not be available for the recommendation process which leads to cold start problem. This research work proposes a knowledge based recommender system to address cold start problem where previous rating are not required for recommendation. This problem is related to recommendations for housing users or new items. In case of new users, the system does not have information about their preferences in order to make recommendations. A model is proposed known a knowledge based recommender system with similarity techniques and prediction mechanisms that provide the necessary means of retrieving recommendations. The proposed approach incorporates case based reasoning that uses similarity measures function and weight to retrieve items from the system that are similar to the specified items attribute by the users. The experiments show the performance of the proposed system through actual use and an online survey form attached to the developed application. It reveals the advantages of the proposed solution by providing recommendations to potential home buyers and tenants by taking into consideration of the main factors users consider important before getting a house.
