Capacity Forecast

Transportation capacity planning happens through gut feel and reactive problem-solving. When a big shipment surge is coming, the operations manager thinks 'we'll probably need more trucks next month' but there's no documented forecast. Capacity shortfalls are discovered when they happen, not predicted in advance.

None — AI cannot forecast capacity needs or recommend proactive carrier procurement because no capacity forecast data exists.

Capacity forecasts exist as rough spreadsheet notes. The transportation manager jots down 'Q3 will be busy, probably need 20% more trucks' or 'December spike coming.' The forecasts are qualitative, updated sporadically, and lack the structure needed for procurement planning. Different people forecast in different ways.

AI could read forecast notes but inconsistent formats and vague estimates make automated procurement planning unreliable. Converting 'busy season' into specific carrier capacity requirements requires manual interpretation.

Capacity forecasts are stored in a structured format with consistent fields. Each quarter, the planning team creates forecasts showing expected shipment volumes by mode, lane group, and equipment type for the next 6 months. Forecasts include baseline volume and seasonal adjustment factors. A procurement manager can see 'we'll need 15% more reefer capacity in Q4.'

AI can generate procurement timing recommendations and identify capacity gaps based on forecasts. Cannot optimize forecast accuracy or link forecasts to actual procurement decisions because forecast performance isn't tracked.

Capacity forecasts are comprehensive entities that combine predictions with validation and action tracking. Each forecast includes volume predictions by lane and equipment, procurement recommendations, actual vs. forecasted comparison, and links to RFPs launched based on the forecast. A procurement manager can query 'show me forecasts where we under-procured capacity and paid spot market premiums' and learn from forecast errors.

AI can improve forecast accuracy from historical patterns, recommend optimal procurement timing, and identify systematic forecasting biases. Cannot yet generate forecasts automatically from demand signals because forecasting models remain implicit.

Capacity forecasts are schema-driven entities with machine-readable forecasting models. Growth assumptions, seasonality factors, demand drivers, scenario parameters, and confidence intervals are all expressed in structured formats. Each forecast documents its methodology, data sources, and uncertainty ranges. An AI agent can generate forecasts autonomously by applying forecasting models to current demand trends and market conditions.

AI can autonomously generate capacity forecasts, recommend procurement strategies, and trigger RFPs at optimal timing. Can quantify forecast uncertainty and adjust procurement plans based on risk tolerance. Full autonomous capacity planning is possible for routine procurement cycles.

Capacity forecasts are living predictions that update in real-time. When customer orders increase, forecasts automatically adjust capacity needs. When market rates spike, forecasts recalibrate procurement timing. When carrier performance changes, forecasts update qualification requirements. The forecast is a real-time capacity intelligence system, not a static planning document.

Fully autonomous capacity planning. AI continuously forecasts needs, triggers procurement at optimal timing, adjusts contracts based on demand shifts, and maintains optimal capacity portfolios in real-time.

Ceiling of the CMC framework for this dimension.