TalentJobRadar: Advanced Data-Driven Recommendations for In-Demand QA Soft Skills and Career Opportunities

Introduction: Software Quality Assurance (QA) is essential to ensure that software products meet predefined requirements. While QA tasks are technical, soft skills play a crucial role in project success, product quality, and the productivity of QA professionals. Objectives: The main objective of this work is to provide a job and skill recommendation tool focused on the Brazilian QA market. Methods: Data was extracted from 2,164 LinkedIn job postings using a data-driven, inductive approach, combining both manual and automated processes. Job descriptions and users’ skills were mapped into binary vectors for comparison. The tool displays job recommendations in a card format, showing company name, required skills, LinkedIn links, and the user’s suitability for the position. Additionally, it suggests skills for improvement and highlights the top three skills associated with the user’s current soft skills, presenting a radar chart that shows job availability by seniority level. Evaluation: We conducted a preliminary evaluation of the tool using 45 synthetic profiles representing varying skill levels to simulate diverse user scenarios, allowing us to assess the system’s adaptability and effectiveness. Job recommendations demonstrated notable precision, recall, and F1-score values, while skill recommendations showed positive results in terms of relative coverage, precision, and relevance. However, applying filters led to a decrease in overall metrics, highlighting limitations in filtered recommendations. Conclusion: The tool shows promise in helping QA professionals at various experience levels identify relevant job opportunities and areas for skill enhancement. Although filtered recommendations present limitations, the system effectively highlights suitable positions and skills for development, supporting employability in the QA field. Future improvements include refining filtered recommendation accuracy and expanding to technical skill recommendations.