A dataset of 10,765 hires reveals that not a single resume keyword can actually predict how well an employee will perform on the job.
April 23, 2026
Original Paper
Decision Traces: What Multi-System Data Fusion Reveals About Institutional Knowledge in Enterprise Hiring
arXiv · 2604.19819
The Takeaway
Corporate screening systems rely on specific keywords to filter through thousands of job applications. These keywords are often useless or even anti-predictive of actual job success. Hiring managers assume that finding the right buzzwords indicates a high-performing candidate. In reality, the automated systems are filtering out talent based on arbitrary criteria that have no connection to performance. Companies are likely missing out on their best potential employees because they rely on algorithmic shorthand.
From the abstract
Enterprise hiring systems generate data across multiple disconnected platforms: applicant tracking systems (ATS) record candidate profiles, human resource information systems (HRIS) record performance outcomes, and behavioral assessments capture personality and behavioral dimensions. Each system operates independently, and the reasoning behind hiring decisions is lost when managers retire, transfer, or leave. Decision traces are structured evidence chains connecting screening inputs, assessment