Predicting Accountants’ Behaviour Using a K-Nearest Neighbours (KNN) Model: A Machine Learning Approach

The study of this paper proposes a K-Nearest Neighbours (KNN)-based classification model to predict accountants’ behavioural responses to new technological paradigms, such as machine learning tools in auditing. Data were collected from professional accountants across Nigeria using a structured survey instrument adapted from the Unified Theory of Acceptance and Use of Technology (UTAUT) and the Technology Readiness Index (TRI). The model was trained using labelled data on behavioural responses and evaluated using standard classification metrics. Results showed that the KNN model achieved an accuracy of 99.9 %, with precision and recall metrics indicating its robustness in classifying resistant and receptive behaviours. These findings suggested that KNN can serve as a practical tool for strategic HR and IT planning in accounting firms.