WFS deploys AI forecasting tool to enhance cargo planning accuracy

• Worldwide Flight Services (WFS), a SATS company, has launched a machine learning-powered forecasting tool that predicts air freight volume by flight, truck and day with up to 98 percent accuracy.
• Trained by a decade of operational data, the Performance Management – Machine Learning Forecast (PMP MLF) platform now supports 75 warehouses in 13 countries, helping WFS proactively align staffing and resources. By replacing manual estimates with accurate daily data on tonnage, ULDs, and part counts, WFS reduces SLA violations, labor inefficiencies, and overtime.
• The second phase of the rollout adds visual dashboards, tighter workforce integration, and customer-level co-planning tools, marking a significant shift toward predictive and data-driven merchandise handling.

Worldwide Flight Services (WFS), a SATS company, has developed a new digital tool using machine learning algorithms trained on 10 years of operational data to deliver highly accurate forecasts of cargo volumes by flight, truck and day, providing each warehouse with accurate data to align workforce and resources in advance.

The air freight industry has long struggled with accurate forecasting due to fluctuating volumes. Work planning often relies on manual estimates and historical averages, which can result in a 10% to 15% gap between staffing levels and actual workload, resulting in inefficiency, reactive processes, and inconsistent service quality.

The Performance Management – Machine Learning Forecast (PMP MLF) platform helps WFS accurately forecast volumes using intelligence based on the processing of more than 3 million air waybills and historical records of air and truck traffic, including seasons, holidays and cargo types.

Currently providing forecasts across 9,842 flights and 6,216 truck movements per week across 75 depots in 13 countries, the system produces daily forecasts of tonnage, ULDs and number of pieces, broken down by transportation mode (freight, passenger, and road feeder services), flight or truck number, customers, and warehouse location. These forecasts are fed directly into station-level planning tools, giving each site clear and reliable forward-looking data.

Using the PMP MLF tool, WFS can detect and plan for significant increases in volume early, adjust resources proactively, and move labor between teams or locations with greater flexibility. This reduces SLA violations due to understaffing or overload and avoids unnecessary overtime or idle time.

The data collected shows that the tool outperforms other forecasting models with an accuracy range of 92-98%, even during irregular demand periods.

Early preparation of the workload with accurate data creates operational certainty and means that WFS operational teams are less reactive and more strategic in meeting customer service requirements. Summer 2025 saw the launch of the second phase of the tool, with further digital enhancements, including:

• Enhanced dashboards and visual analytics
• Tighter integration with workforce management and rostering tools
• Customer level forecasting to participate in planning for volume peaks

“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 improve workforce allocation, enhance service levels, and reduce operational waste across our global air cargo network – and we’ve been inspired by the results. Predictive planning and accurate forecasting means we’ve achieved a fundamental shift in how cargo handlers plan,” said Jamie Daniel Hansen, vice president. Senior Head of Operational Excellence:

“All of these benefits make sense to our customers. They translate into fFewer delays due to staffing issues, improved service consistency, transparency, and capabilities backed by pre-shared data. THe added that this is the kind of digital innovation they want to see.