Sibusiso Mzulwini and Tendani Lavhengwa, Tshwane University of Technology, RSA

This paper aims to enhance aviation safety by identifying and addressing pilot performance weaknesses through data-driven techniques, focusing on the strategic adoption of predictive analytics in pilot training across Southern Africa, particularly in South Africa, Namibia, and Botswana. The main objective is to utilize advanced technologies like Natural Language Processing (NLP) and machine learning (ML) to analyze aviation incident reports and identify patterns of pilot errors and operational risks. The study's results highlight vital insights, which pave the way for tailored training programs designed to mitigate risks. The achievements of the study include filling a non-empirical gap by applying the Diffusion of Innovations (DOI) framework to examine the adoption of predictive analytics alongside recommendations for standardized reporting, specialized training modules, and the integration of weather analytics. These outcomes demonstrate the transformative potential of predictive analytics in improving pilot training and enhancing safety in the Southern African aviation sector.

Predictive Analytics, pilot training, Diffusion of Innovations (DOI), Aviation Safety & Natural Language Processing (NLP).