K-Nearest Neighbor Algorithm for Data-Driven IT Governance: A Case Study of Project Outcome Prediction

Abstract

This study examines the application of the k-Nearest Neighbor (k-NN) algorithm for predicting IT project outcomes to support data-driven decision-making in IT governance. The algorithm was applied to a dataset of historical projects from a mid-sized technology company. Despite limitations like sensitivity to parameter tuning, the simplicity and interpretability of k-NN demonstrate its potential as an IT governance decision tool. However, the single case study design restricts generalizability. Further research should explore ensemble approaches to improve robustness, compare k-NN with other methods, and assess its effectiveness across diverse organizational contexts.