https://doi.org/10.1140/epjds/s13688-025-00527-z
Research
Uncovering and estimating complementarity in urban lives
School of Computing and Information, Department of Informatics and Networked Systems, University of Pittsburgh, 135 North Bellefield Avenue, 15260, Pittsburgh, PA, USA
Received:
25
May
2024
Accepted:
18
January
2025
Published online:
3
February
2025
We typically think of the demand volume for a business in a city as a function of basic characteristics, such as the type of business, the quality of the product or service offered and its pricing. In addition, factors related to the urban environment, such as population density and accessibility are also crucial and have been considered in the literature. However, these considerations have typically been at the macro level. In this work we are interested in exploring the complementarity between specific (pairs) of venues. Simply put, venue B is complementary to venue A, if customers are more probable to visit venue B after being at venue A. This can increase the traffic for a business beyond the demand expected from the aforementioned factors, and it has been largely ignored in the literature. In this study we take a simulation-based approach to estimate this complementarity. We perform our simulations and analysis on two different spatial levels, namely, the venue level, as well as, the urban area level (e.g., zip code, neighborhood, etc.). The estimated complementarity provides insights for business owners and urban planners that can allow them to satisfy more demand, which consequently can increase the revenue for the businesses, but also can create more convenient urban navigation for city dwellers.
Key words: Complementarity / Urban computing / Local business / Mixed-effects model / Graph neural network
© The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.