LinkedIn Salary: A System for Secure Collection and Presentation of Structured Compensation Insights to Job Seekers

Online professional social networks such as LinkedIn have enhanced the\nability of job seekers to discover and assess career opportunities, and the\nability of job providers to discover and assess potential candidates. For most\njob seekers, salary (or broadly compensation) is a crucial consideration in\nchoosing a new job. At the same time, job seekers face challenges in learning\nthe compensation associated with different jobs, given the sensitive nature of\ncompensation data and the dearth of reliable sources containing compensation\ndata. Towards the goal of helping the world's professionals optimize their\nearning potential through salary transparency, we present LinkedIn Salary, a\nsystem for collecting compensation information from LinkedIn members and\nproviding compensation insights to job seekers. We present the overall design\nand architecture, and describe the key components needed for the secure\ncollection, de-identification, and processing of compensation data, focusing on\nthe unique challenges associated with privacy and security. We perform an\nexperimental study with more than one year of compensation submission history\ndata collected from over 1.5 million LinkedIn members, thereby demonstrating\nthe tradeoffs between privacy and modeling needs. We also highlight the lessons\nlearned from the production deployment of this system at LinkedIn.\n