Forecasting Manpower Planning Using the CRISP-DM Method and Machine Learning Algorithm: A Case Study of Tiki Jalur Nugraha Ekakurir (JNE) Company

Abstract

Introduction: The logistics industry faces significant fluctuations in demand, particularly during peak seasons, making effective manpower planning essential to maintaining service quality and controlling operational costs. Poor workforce planning can lead to inefficiencies such as overstaffing, which increases costs, or understaffing, which negatively impacts delivery performance. To address these challenges, this research focuses on developing a predictive analytics model for workforce planning at Tiki Jalur Nugraha Ekakurir (JNE) Company, a leading logistics company in Indonesia. By leveraging machine learning and dashboard modeling, the study aims to enhance decision-making and improve workforce efficiency during high-demand periods.

Objectives: This research is driven by the need to develop a predictive analytics model capable of forecasting workforce requirements during peak seasons. The goal is to optimize manpower allocation based on shipment trends and provide real-time insights through an interactive dashboard.

Methods: A quantitative approach is applied, following the CRISP-DM framework, which includes business understanding, data preparation, model development, and evaluation. The dataset consists of historical shipment records, workforce availability, and external factors like public holidays and promotional events. Machine learning models, including linear regression and Gradient Boosted Trees (GBT), are implemented using KNIME Analytics Platform to enhance forecasting accuracy.

Results: The GBT model with six lag columns provided the most accurate predictions, achieving a Mean Absolute Percentage Error (MAPE) below 5%. To support real-time decision-making, a Manpower Planning Dashboard was developed, visualizing shipment trends, staffing requirements, and workforce distribution. By utilizing this system, JNE Company was able to improve task allocation by 15% and reduce overtime costs by 10%, demonstrating the benefits of predictive analytics in workforce management.

Conclusions: In summary, this study successfully introduces a data-driven approach to manpower planning by integrating predictive analytics with an interactive dashboard. The model enhances workforce distribution, minimizes inefficiencies, and optimizes logistics operations. Moving forward, JNE Company can further refine this system by incorporating real-time data updates, considering external factors like weather conditions and customer demand fluctuations, and expanding predictive capabilities to other areas such as warehouse management and route optimization. By embracing these innovations, JNE Company can strengthen its market position, improve operational efficiency, and ensure optimal workforce allocation, particularly during peak seasons.