A fuzzy asymmetric TOPSIS model for optimizing investment in online advertising campaigns

Abstract

The high penetration of the Internet and e-commerce in Spain during recent years has increased companies' interest in this medium for advertising planning. In this context Google offers a great advertising inventory and perfectly segmented content pages. This work is concerned with the optimization of online advertising investments based on pay-per-click campaigns. Our main goal is to rank and select different alternative keyword sets aimed at maximizing the awareness of and traffic to a company's website. The keyword selection problem with online advertising purposes is clearly a multiple-criteria decision-making problem additionally characterized by the imprecise, ambiguous and uncertain nature of the available data. To address this problem, we propose a technique for order of preference by similarity to ideal solution (TOPSIS)-based approach, which allows us to rank the alternative keyword sets, taking into account the fuzzy nature of the available data. The TOPSIS is based on the concept that the chosen alternative should have the shortest distance from the positive ideal solution and the longest distance from the negative ideal solution. In this work, due to the characteristics of the studied problem, we propose the use of an asymmetric distance, allowing us to work with ideal solutions that differ from the maximum or the minimum. The suitability of the proposed model is illustrated with an empirical case of a stock exchange broker's advertising investment problem aimed at generating awareness about the brand and increasing the traffic to the corporative website.