SBIR Phase I: An Adaptive AI-Driven Career Exploration Platform

The broader/commercial impact of this SBIR Phase I project is to ensure all Americans have access to 21st century careers while addressing a gap in workforce development through an adaptive, AI-driven career exploration platform which provides personalized career guidance for students in secondary and post-secondary education. This unique approach to career readiness will reduce unemployment and skill mismatches across the nation by addressing critical stages in career lifecycle of awareness, interest, and readiness.

By enhancing the technological infrastructure supporting career development and fostering a more adaptive, skilled, and competitive workforce, the project aligns with national interests towards accelerated access to meaningful career choices and lower rates of unemployment in critical . The market opportunity for this project focuses on educational institutions and workforce development agencies, with the first market segment being high schools and post-secondary institutions.

By year three of deployment, this solution is projected to improve career readiness for thousands of individuals, improving labor market alignment, which will create significant economic value by creating a more engaged and aligned workforce. This project will advance scientific understanding by developing and applying advanced learning theories and data-driven models to support open-field decision-making processes, fostering better career outcomes for all.

This Small Business Innovation Research (SBIR) Phase I project focuses on developing a data-driven platform to address the challenge of career discovery and decision-making in complex and evolving job markets. The project integrates advanced learning theories to design state-of-the-art artificial intelligence and data visualization technologies to design and validate a novel system to contextualizes large datasets inclusive of such as labor market trends, job qualifications, and career pathways, into actionable insights for users.

The approach leverages principles of machine learning, hierarchical reinforcement learning, and retrieval-augmented generation to create an adaptive platform capable of personalizing recommendations and guiding users through informed decision-making towards career identification, readiness, and success. Anticipated technical results include the development of scalable algorithms for hierarchical data modeling, a robust user-interface prototype, and pilot-tested outcomes demonstrating improved alignment between user preferences and career engagement.

The research will provide foundational advancements in integrating educational, psychological, and data science principles, with implications for creating more effective, scalable solutions in career discovery and workforce development.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.