Data Mining-based Real-Time User-centric Recommender System for Nigerian Tourism Industry

The tourism information system in Nigeria is not novel. What is novel is the need to develop reliable real-time recommender systems that can adequately aid tourists in their decisions. Several researchers have proposed various models. However, there are still issues about the applicability, effectiveness, efficiency, and reliability of the existing recommenders in the Nigerian tourism sector. This work is aimed at developing an improved model for real-time tourism recommender in Nigeria based on a data mining model. The objectives include the development of a data mining model for real-time reliable user-centric tourism recommendation and evaluation of the recommender system. To achieve these, a supervised machine learning-based classifier is modelled. The classifier system is evaluated using four thousand (4,000) datasets acquired from online and physical Nigerian tourism sources. Nine machine learning algorithms are compared during the testing process based on accuracy and other standard performance metrics. Experimental results show that the PART algorithm outperforms all other algorithms with an accuracy of 91.65%, F-Measure of 0.917, true positive rate of 0.913, the false-positive rate of 0.029, and the precision of 0.917, and recall of 0.917. In terms of efficiency, it also records the least time-to-model of 0.02 seconds. The rules generated from this algorithm are incorporated into the design of a prototype to test the recommender. The usefulness and efficiency scores based on test cases involving 20 participants prove that the recommender system would be a veritable tool for tourism in Nigeria.