Campaign Optimization through Mobility Network Analysis

Campaign Optimization through Mobility Network Analysis

Yaniv Altshuler (Endor, Israel), Erez Shmueli (Tel-Aviv University, Israel), Guy Zyskind (Massachusetts Institute of Technology, USA), Oren Lederman (Massachusetts Institute of Technology, USA), Nuria Oliver (Telefonica Research, Spain) and Alex “Sandy” Pentland (Massachusetts Institute of Technology, USA)
Copyright: © 2015 |Pages: 43
DOI: 10.4018/978-1-4666-8465-2.ch002

Abstract

Optimizing the use of available resources is one of the key challenges in activities that consist of interactions with a large number of “target individuals”, with the ultimate goal of affecting as many of them as possible, such as in marketing, service provision and political campaigns. Typically, the cost of interactions is monotonically increasing such that a method for maximizing the performance of these campaigns is required. This chapter proposes a mathematical model to compute an optimized campaign by automatically determining the number of interacting units and their type, and how they should be allocated to different geographical regions in order to maximize the campaign's performance. The proposed model is validated using real world mobility data.
Chapter Preview
Top

Background

In recent years the social sciences have been undergoing a digital revolution, heralded by the emerging field of “computational social science”. Lazer et. al (2009) describe the potential of computational social science to increase our knowledge of individuals, groups, and societies, with an unprecedented breadth, depth, and scale. Computational social science combines the leading techniques from network science (Barabasi & Albert, 1999; Newman, 2003; Watts & Strogatz, 1998) with new machine learning and pattern recognition tools specialized for the understanding of people’s behavior and social interactions (Eagle et al., 2009).

Purchase this chapter to continue reading all 43 pages >

Complete Chapter List

Search this Book:
Reset