Causal Synthetic Data Generation in Recruitment

2025-11-20

AI Summary

Recruitment suffers from a scarcity of high-quality, publicly available datasets due to privacy-sensitive attributes (e.g., gender, age) embedded in resumes—severely hindering the development of fair and interpretable candidate ranking models. To address this, we propose a synthetic data generation method grounded in dual Causal Generative Models (CGMs): one modeling job-posting mechanisms and the other modeling resume-generation mechanisms. Leveraging domain knowledge, we construct a structured causal graph (a Bayesian network) that explicitly encodes bias propagation pathways and enables their targeted intervention. This work is the first to jointly model causal relationships and bias sources in recruitment data while supporting controllable, bias-aware synthesis. Empirical evaluation confirms that the generated data faithfully captures real-world causal dependencies in hiring and effectively supports fairness auditing and attribution analysis for ranking algorithms under controlled bias conditions. Our approach establishes a reproducible, auditable data infrastructure for trustworthy AI research in privacy-sensitive domains.

Technology Category

• Machine Learning: Causal Learning
• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The importance of Synthetic Data Generation (SDG) has increased significantly in domains where data quality is poor or access is limited due to privacy and regulatory constraints. One such domain is recruitment, where publicly available datasets are scarce due to the sensitive nature of information typically found in curricula vitae, such as gender, disability status, or age. % This lack of accessible, representative data presents a significant obstacle to the development of fair and transparent machine learning models, particularly ranking algorithms that require large volumes of data to effectively learn how to recommend candidates. In the absence of such data, these models are prone to poor generalisation and may fail to perform reliably in real-world scenarios. % Recent advances in Causal Generative Models (CGMs) offer a promising solution. CGMs enable the generation of synthetic datasets that preserve the underlying causal relationships within the data, providing greater control over fairness and interpretability in the data generation process. % In this study, we present a specialised SDG method involving two CGMs: one modelling job offers and the other modelling curricula. Each model is structured according to a causal graph informed by domain expertise. We use these models to generate synthetic datasets and evaluate the fairness of candidate rankings under controlled scenarios that introduce specific biases.

Problem

• Generating synthetic recruitment data with causal relationships
• Addressing data scarcity in sensitive recruitment information
• Evaluating fairness in candidate ranking algorithms

Innovation

• Causal Generative Models for synthetic data
• Dual CGM structure for job offers and CVs
• Domain-expertise causal graphs control bias