TraVaS: Differentially Private Trace Variant Selection for Process Mining

TL;DR

This paper presents a new differentially private method for releasing trace variants in process mining, improving utility and privacy trade-offs over existing prefix expansion techniques.

Contribution

The authors introduce a direct trace variant release approach using anonymized partition selection, addressing computational complexity and variant fidelity issues.

Findings

Outperforms state-of-the-art methods in data utility

Reduces computational complexity in trace variant release

Maintains high privacy guarantees in process mining data

Abstract

In the area of industrial process mining, privacy-preserving event data publication is becoming increasingly relevant. Consequently, the trade-off between high data utility and quantifiable privacy poses new challenges. State-of-the-art research mainly focuses on differentially private trace variant construction based on prefix expansion methods. However, these algorithms face several practical limitations such as high computational complexity, introducing fake variants, removing frequent variants, and a bounded variant length. In this paper, we introduce a new approach for direct differentially private trace variant release which uses anonymized \textit{partition selection} strategies to overcome the aforementioned restraints. Experimental results on real-life event data show that our algorithm outperforms state-of-the-art methods in terms of both plain data utility and result utility preservation.