Integrating a Generative AI Applicant Tracking System for CBTA

To streamline the recruitment process – from job posting to candidate selection – the Airline Pilot Club incorporates a Generative AI-enhanced applicant tracking system (ATS) which allows for more nuanced understanding and matching of candidate capabilities with job requirements. Advanced data analytics are applied to profiling, predictive modeling for role compatibility, and AI-driven insights for decision support in recruitment. This leads to more targeted recruitment and the foundation for creating highly personalized, evidence-based training (EBT) programs.

The APS approach utilizes Generative AI algorithms to analyze detailed candidate profiles, which include not just educational backgrounds and professional experiences but also soft skills, personality traits, and potential for growth.

The Generative AI models are trained to match candidate profiles with specific competencies – as defined by ICAO, IATA and others – and characteristics required for various roles within the aviation industry.

The goal is to ensure a high degree of compatibility between the job requirements and the qualities of the candidates (intrinsic and acquired), enhancing the likelihood of success and job satisfaction.

Some of the competency-based training and assessment (CBTA) shortcomings which are exposed by the data analysis include:

Application of Knowledge (KNO) – While not explicitly mentioned, the challenges in applying briefs and procedures suggest gaps in fundamental knowledge. In-depth knowledge of complex aircraft systems in multi-engine, larger aircraft has also been identified for commercial pilot license Instrument rating (CPL IR) candidates with no exposure to multi-engines or complex systems.

Application of Procedures (PRO) – Candidates demonstrate a lack of depth in briefing techniques and proper application of procedures, evident in their approach to crew briefs.

Communication (COM) – Issues with both internal cockpit communication and external communication with air traffic control (ATC) and operations, reflecting challenges in effective verbal, non-verbal, and written communication.

Aircraft Flight Path Management, Manual (FPM) –Difficulty in manually managing the flight path during instrument flight rules (IFR) approaches, as candidates chase course deviation indicator / ground speed (CDI / GS) to minimums, indicates a need for improvement in this competency. Flight experience and currency has a significant impact.

Aircraft Flight Path Management, Automation (FPA) –There is no specific mention of automation management in the findings as the evaluation is entirely performed without automation but it is clear that some candidates have managed to pass type ratings using the automation of the aircraft to hide deficiencies in workload management in Aircraft Flight Path Management, Manual. Also the reliance on specific approaches and underutilization of ATC resources may imply issues here.

Leadership and Teamwork (LTM) – Internal cockpit communication challenges and crew resource management (CRM) issues point to a need for better leadership and teamwork skills.

Problem Solving and Decision Making (PSD) – The use of the FORDEC mnemonic (Facts, Options, Risks and benefits, Decision, Execution, Check) without effective decision execution suggests deficiencies in problem-solving and decision-making competencies.

Situational Awareness (SAW) – Candidate’s reluctance to adopt visual patterns / approaches and ineffective use of briefs indicate a lack of situational awareness.

Workload Management (WLM) – Excessive internal communication and mis-prioritization of communications contribute to workload management issues.

Excerpted from The Robot in the Simulator: Artificial Intelligence in Aviation Training by Rick Adams, FRAeS – https://aviationvoices.com/shop/