<![CDATA[This study presents a hybrid framework combining Principal Component Analysis (PCA) and Multi‐Objective Complexity Prediction (MPK) to extract actionable insights from multidimensional human resource (HR) data in plantation companies. Initially, PCA reduces nine original HR variables including age, tenure, absenteeism, leave, harvest yield, and performance scores to four principal components that capture over 90 % of total variance. These reduced features form the solution space for MPK agents, each of which simultaneously optimizes three objectives: absenteeism risk (predicted via SVR), performance score (via linear regression), and workload imbalance. The model is tuned with 5-fold cross-validation on 80 % of the data, yielding MAE ≈ 6.5 days and R² ≈ 0.82 for absenteeism, MAE ≈ 4.2 points and R² ≈ 0.78 for performance, MAPE ≈ 15 % for workload imbalance, and a Pareto‐front hypervolume of ≈ 0.90. Validation on the remaining 20 % hold-out set confirms similar generalization (hypervolume ≈ 0.88). Sensitivity analysis with ± 10 % input noise demonstrates the approach’s robustness under moderate perturbations. These results illustrate that PCA–MPK can both streamline high-dimensional HR datasets and deliver reliable, multi-objective forecasts to inform strategic workforce planning.]]>
Copyrights © 2026
