18th AIAI 2022, 17 - 20 June 2022, Greece

A Multi-Objective Optimization Algorithm for Out-of-Home Advertising

Nader Nader, Rafael Alexandrou, Iasonas Iasonos, Andreas Pamboris, Harris Papadopoulos, Andreas Konstantinidis


  This paper presents a Multi-Objective Optimization (MOO) approach for Out-of-Home (OOH) advertising campaign billboard selection. In particular, it exploits a large variety of features from different sources, such as Geographic Information Systems (GIS) and demographics data, for the construction of billboard profiles that take into account all factors that affect the attractiveness of each billboard both in general and for different types of customers. These profiles are utilized by a Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) hybridized with two problem specific techniques to provide a set of non-dominated solutions, each corresponding to a different allocation of billboards to a given campaign. The experimental results enable exploration of the trade-offs between multiple conflicting objectives (e.g., cost vs. coverage) as well as demonstrate that the two problem specific techniques have improved the conventional MOEA/D performance with respect to both convergence and diversity.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.