iarjetIARJETIARJET2708-5163https://doi.org/10.47310/iarjet.2021.v02i01.002Expert Decision Support System for the Prediction of Staff Promotion Using Mutual Information Gain Enhanced Naïve Bayes ModelOlusolaA.OlabanjoAshiriboS.WusuDepartment of Computer Science, Lagos State University, Lagos, NigeriaDepartment of Mathematics, Lagos State University, Lagos, NigeriaPersonnel management is a key factor in an organization’s Human Relations (HR). The global economic meltdown in recent years, the rise in the application of technology in the area of business intelligence and the meteoric rise in the rate of competitions in business sectors, among others, have given rise to the need for organizations to restructure, re-strategize and reposition their method of running businesses across their established units; HR inclusive. The need for effective service delivery, enhanced decision making support system, non-biased staff relations strategy, effective and staff-oriented policy making, adequate business ethics and efficient enterprise resource planning necessitates the need to have in place an effective support mechanism for the HR department in the determination of promotion of the employees in its care. In this work, we aimed to develop an enhanced Naïve Bayes model for the prediction of staff promotion in an organization. We obtained an HR dataset from Kaggle (https://kaggle.com) – an online repository which contained staff’s personal and performance attributes and a class indicator of whether they are promoted or not. A Naïve Bayes (a probabilistic) model was developed for the preprocessed dataset. The dimension of the dataset was also reduced and its impact was assessed. The developed model gave accuracy of 91% for the full feature set and 93% for the reduced dataset. The specificity (79%) and the Negative Predicted Value (27%) for the Non-Promoted class shows that there is need for more datasets for this target class. Results also showed that the enhanced Naïve Bayes model performed better than the regular Naïve Bayes model. This work brings to the awareness of the employees and employers alike the attributes that must be given a higher attention for promotion purpose. Mutual-Information-Gain-enhanced Naïve Bayes model has proven to be a promising model in achieving a significant level of accuracy in predicting if a staff is to be promoted or not.