An Approach to Recommendation Systems Using Scalable Association Mining Algorithms on Big Data Processing Platforms: A Case Study in Airline Industry

In recent years, ancillary services have become essential to increase revenue considering the fierce competition in the airline industry. Low-Cost Carriers generally prefer to sell tickets and ancillary services such as seat selection, excess baggage, a-la-carte meals, Wi-Fi internet access separately. Full-Service Carriers prefer to sell tickets as branded fares and offer several choices by grouping the most preferred ancillary services. To the best of our knowledge, there is no recommendation system for recommending ancillary services to increase the revenue of the airline companies. This paper proposes a methodology based on Lambda Architecture as a recommendation system that runs on a distributed big data platform. The proposed method utilizes association mining algorithms. We use scalable association mining algorithms implemented for the big data processing platforms. To facilitate testing of the proposed method, we implement a prototype application. We conduct an experimental study on the prototype to investigate the performance of the proposed methodology using accuracy and running times. The results indicate that the proposed method proves to be useful and has negligible processing overheads.