# Graph distances for determining entities relationships: a topological approach to fraud detection

arXiv: https://arxiv.org/abs/1905.08040 · HTML: https://mlsanity.com/paper/1905.08040/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2019.

## Built on by (most cited first, 1 of 1)

- [Metric spaces of walks and Lipschitz duality on graphs](https://mlsanity.com/paper/2508.19709/) (2025)

## Abstract (arXiv)

Given a set Omega and a proximity function φ: Omega × Omega → mathbb R^+, we define a new metric for Omega by considering a path distance in Omega, that is considered as a complete graph. We analyze the properties of such a distance, and several procedures for defining the initial proximity matrix ( φ(a,b) )(a,b) ∈ Omega × Omega. Our motivation has its roots in the current interest in finding effective algorithms for detecting and classifying relations among elements of a social network. For example, the analysis of a set of companies working for a given public administration or other figures in which automatic fraud detection systems are needed. Using this formalism, we state our main idea regarding fraud detection, that is founded in the fact that fraud can be detected because it produces a meaningful local change of density in the metric space defined in this way.