WFS uses machine learning to forecast cargo volumes and staffing

Worldwide Flight Services (WFS), a SATS company, has developed a digital tool that uses machine learning to forecast cargo volumes and improve workforce planning. The system has been trained on 10 years of operational data and provides accurate forecasts by flight, truck and day, helping each warehouse align labour and resources in advance.

Accurate forecasting has been a long-standing challenge for the air cargo industry because volumes are volatile. Labour planning has often relied on manual estimates and historical averages, leading to a 10-15 percent gap between staffing levels and actual workload. This has resulted in inefficiencies, reactive operations and variations in service quality.

The Performance Management Platform – Machine Learning Forecast (PMP MLF) generates forecasts using intelligence from more than three million air waybills as well as historical flight and truck movement records. The system takes into account seasonality, holidays and cargo types to improve accuracy.

The tool currently provides forecasts for 9,842 flights and 6,216 truck movements every week across 75 warehouses in 13 countries. It produces daily forecasts of tonnage, ULDs and piece count, broken down by transport mode, flight or truck number, customer and warehouse. These forecasts feed directly into station-level planning tools so that each location has clear forward-looking data.

Using PMP MLF, WFS can detect and prepare for volume surges in advance and adjust labour between teams or sites when needed. This helps reduce service level breaches caused by under- or over-staffing and avoids unnecessary overtime or idle time.

Data from WFS shows the tool has an accuracy rate of 92-98 percent, even during irregular demand periods. The system allows teams to plan early and operate more strategically, rather than reacting to workload changes.

Phase two of the tool was rolled out in summer 2025 with further digital improvements, including enhanced dashboards and visual analytics, closer integration with workforce management tools and customer-level forecasting.

“For many years, cargo handlers have relied on manual scheduling, Excel spreadsheets or basic rolling averages for forecasting – and we know some still do. By leveraging machine learning within a complex operational network, our goal was to replace reactive guesswork with data-driven clarity to optimise workforce allocation, enhance service levels and reduce operational waste across our global air cargo network – and we are inspired by the results. Predictive planning and precision forecasting means we have achieved a fundamental transformation in how cargo handlers plan and operate,” said Jimi Daniel Hansen, SVP Operational Excellence.

“All of these benefits are meaningful to our customers. They translate into fewer delays due to staffing issues, improved service consistency and transparent, data-backed capacity shared in advance. This is the type of digital innovation they want to see,” he added.