Multi-objective Consensus Clustering Framework for Flight Search Recommendation

Abstract

In the travel industry, online customers book their travel itinerary according to several features, like cost and duration of the travel or the quality of amenities. To provide personalized recommendations for travel searches, an appropriate segmentation of customers is required. Clustering ensemble approaches were developed to overcome well-known problems of classical clustering approaches, that each rely on a different theoretical model and can thus identify in the data space only clusters corresponding to this model. Clustering ensemble approaches combine multiple clustering results, each from a different algorithmic configuration, for generating more robust consensus clusters corresponding to agreements between initial clusters. We present a new clustering ensemble multi-objective optimization-based framework developed for analyzing Amadeus customer search data and improve personalized recommendations. This framework optimizes diversity in the clustering ensemble search space and automatically determines an appropriate number of clusters without requiring user's input. Experimental results compare the efficiency of this approach with other existing approaches on Amadeus customer search data in terms of internal (Adjusted Rand Index) and external (Amadeus business metric) validations.

Feedback Clustering for Online Travel Agencies Searches: a Case Study

“…For instance, we could consider multiple runs of split and merge operators at each iteration. Lastly, we are working on comparing the impact on flight recommendations of SME and S/M to other frameworks such as ensemble clustering [6]. This would provide further tests for the effectiveness of customizability index, specifically and as a domain-specific feedback.…”

“…The problem of classifying customers in the travel industry by simply relying on flight searches and no prior available classes is addressed in [6]. Therein, the segmentation is achieved by exploiting consensus clustering techniques surveyed in [16].…”

“…We quantify it over each dataset. For each number of clusters k in [2,3,4,5,6,7] we measure the expected relative change over 10 customizability evaluation calls over the same clustering of k clusters.…”

“…For each dataset, methods are called with a number of initial clusters k varying in [2,3,4,5,6,7]. The SME(RSS) and the SME(Custom.)…”