How to Cite:
Vinoth Kumar, "AI-Driven SQA Audit Automation Framework for ASPICE-Compliant Automotive Development Lifecycle" International Journal of Machine Intelligence, Data Science and AI, Vol. 1, No. 1, pp. 10-14, 2026.

Abstract:
The increasing complexity of modern automotive software systems has intensified the demand for robust Software Quality Assurance (SQA) mechanisms aligned with Automotive Software Process Improvement and Capability Determination (ASPICE) standards. Traditional manual audit approaches are often time-consuming, error-prone, and insufficient for handling large-scale automotive software projects involving continuous integration, over-the-air updates, and safety-critical functionalities. This research proposes an AI-driven SQA Audit Automation Framework designed to enhance compliance verification, process monitoring, defect prediction, and audit traceability within the ASPICE-compliant automotive development lifecycle. The framework integrates Artificial Intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP), and predictive analytics to automate evidence collection, process assessment, anomaly detection, and compliance scoring. A comparative evaluation was conducted between traditional manual auditing and the proposed AI-enabled framework across key metrics such as audit accuracy, defect detection rate, compliance validation time, and resource utilization. Experimental findings indicate that the proposed framework improves audit efficiency by 42%, increases compliance accuracy to 96%, and significantly reduces human intervention during process assessments. Furthermore, the study identifies major research gaps in adaptive compliance intelligence and real-time audit orchestration for automotive DevOps ecosystems. The proposed model offers substantial practical implications for automotive OEMs, Tier-1 suppliers, and quality engineering teams aiming to achieve higher ASPICE maturity levels while reducing operational overhead. The framework contributes toward intelligent software governance for next-generation autonomous and connected vehicle systems.

Keywords: Artificial Intelligence, ASPICE, Automotive SPICE, Software Quality Assurance, Audit Automation, Machine Learning, Automotive Software Engineering, Compliance Management, Predictive Analytics, Intelligent Process Monitoring.

References:
[1] Becker, J., Hoffmann, J., & Weber, P. (2021). Intelligent process assessment automation in automotive software engineering. Journal of Systems and Software, 178, 110945.
[2] Kim, S., & Park, H. (2022). Machine learning-based defect prediction for automotive embedded systems. IEEE Access, 10, 44125–44139.
[3] Liu, Y., Zhang, T., & Wang, H. (2024). NLP-driven compliance verification in automotive software requirements engineering. Information and Software Technology, 168, 107394.
[4] Sharma, R., Kulkarni, P., & Iyer, S. (2023). DevOps-enabled ASPICE compliance monitoring for automotive CI/CD ecosystems. Software Quality Journal, 31(4), 1123–1148.
[5] Müller, K., Schneider, F., & Braun, A. (2022). AI-enhanced software quality analytics for safety-critical automotive applications. Empirical Software Engineering, 27(6), 143.
[6] ISO/IEC 330xx. (2021). Process assessment standards for software engineering. International Organization for Standardization.
[7] Automotive SIG. (2022). Automotive SPICE Process Assessment Model Version 4.0. Automotive Special Interest Group.
[8] Singh, A., Verma, R., & Gupta, M. (2023). Predictive analytics for software process compliance in autonomous vehicle systems. Journal of Software Evolution and Process, 35(8), e2481.
[9] Zhao, L., Chen, Y., & Xu, W. (2024). Reinforcement learning-driven adaptive software auditing framework. IEEE Transactions on Software Engineering, 50(2), 221–236.
[10] Patel, D., Narayanan, V., & Bose, R. (2021). Automated evidence collection mechanisms for ASPICE assessments. International Journal of Automotive Technology, 22(5), 1341–1352.
[11] Ahmed, S., Rahman, K., & Lee, J. (2024). AI-based anomaly detection in automotive software lifecycle management. Future Generation Computer Systems, 153, 214–228.
[12] Wang, X., Li, H., & Sun, P. (2023). Intelligent traceability management using deep learning for automotive software systems. IEEE Software, 40(5), 66–74.
[13] Gupta, N., & Rao, S. (2022). Continuous compliance engineering in software-defined vehicles. Journal of Automotive Software Engineering, 5(2), 91–108.
[14] Fernández, P., Costa, M., & Silva, R. (2024). Explainable AI models for safety-critical software auditing. ACM Transactions on Software Engineering and Methodology, 33(1), 1–29.
[15] Chandra, V., & Menon, A. (2023). AI-driven quality governance frameworks for automotive embedded platforms. Computers in Industry, 149, 103921.