Detection of decision-making manipulation in the pairwise comparisons method

TL;DR

This paper introduces three manipulation techniques in pairwise comparison decision-making models and proposes neural network-based detection methods, demonstrating effective identification of manipulations on generated data.

Contribution

It presents the first systematic analysis of manipulation methods in pairwise comparison models and develops neural network detectors for these manipulations.

Findings

Neural networks can effectively detect manipulation methods

Three simple manipulation techniques are identified and analyzed

Detection accuracy is high on generated datasets

Abstract

Most decision-making models, including the pairwise comparison method, assume the decision-makers honesty. However, it is easy to imagine a situation where a decision-maker tries to manipulate the ranking results. This paper presents three simple manipulation methods in the pairwise comparison method. We then try to detect these methods using appropriately constructed neural networks. Experimental results accompany the proposed solutions on the generated data, showing a considerable manipulation detection level.