• Are your demand forecasts consistently off by enough margin to cost you either carrying costs or lost sales?

  • Are you finding out about shipment exceptions at the same time your customer does?

AI for Logistics and Supply Chain

Late shipments, carrier rate surprises, warehouse inefficiency, and demand forecasts built in spreadsheets: these are operations problems that AI can reduce. The question is which problem to solve first and what data you already have to work with.
We build AI systems for logistics and supply chain operations: demand forecasting models, route optimisation, predictive ETAs, carrier rate prediction, exception detection, document extraction from shipping documents, and load optimisation. Every system is scoped against your data and a specific operational outcome.

  • Demand forecasting models that reduce overstock and stockout simultaneously

  • Predicted ETAs and delay alerts before the customer asks where their shipment is

  • Carrier rate prediction so procurement buys at the right time, not the wrong time

  • Document extraction from BOLs, PODs, customs forms, and invoices without manual re-keying

RaftLabs builds AI systems for logistics and supply chain companies including demand forecasting models trained on historical order and external signal data, ML-based route optimisation, predictive ETA engines that surface delay risk before it happens, carrier rate prediction models, warehouse slotting optimisation, exception prediction for in-transit shipments, document extraction from bills of lading and proof of delivery documents, and load optimisation algorithms. Engagements run at a fixed price after a discovery phase that maps your operational data to the AI capability being scoped.

Vodafone
Aldi
Nike
Microsoft
Heineken
Cisco
Calorgas
Energia Rewards
GE
Bank of America
T-Mobile
Valero
Techstars
East Ventures

Operations that see problems before they become costs

Supply chain AI is most valuable when it moves your operation from reactive to anticipatory. Finding out about a delay when your customer does is not a system failure, it is a data and model failure. The information to predict the delay was usually there. The question is whether your system acts on it.

What we build

Demand forecasting models

ML models trained on your historical order data, promotional calendars, and external signals to forecast demand at the SKU and location level. Output is a daily or weekly forecast with confidence intervals, not a single-point estimate. We use gradient boosting models or temporal fusion transformers depending on your data volume and seasonality patterns. Accuracy is measured against your current forecast method and reported before and after deployment.

Route optimisation

ML-based routing that incorporates real-time traffic, weather, historical driver performance, and customer time window constraints. Re-optimises dynamically as conditions change during the day, not just at dispatch. Learns from your historical route outcomes: which lane and stop combinations cause overtime, which routes have a higher late delivery rate, which drivers perform best on which route types. Integrates with your existing TMS or dispatch system via API.

Predictive ETA and exception detection

A model that scores each in-transit shipment against delay probability using carrier, lane, days in transit, weather, and historical exception rates for that carrier-lane combination. High-risk shipments surface before the delay is confirmed, with contributing risk factors. Gives your operations team time to intervene or alert the customer proactively. Reduces the number of customer-reported exceptions by surfacing the signal early.

Carrier rate prediction

Models trained on historical carrier rate data, fuel indices, capacity signals, and seasonal patterns to predict where spot rates are heading. Helps procurement decide when to lock in contract rates and when to stay spot. Reduces transport cost by buying at lower points in the rate cycle rather than reacting to market conditions after the fact. We train these models on public market data combined with your historical rate transactions.

Shipping document extraction

AI that reads bills of lading, proof of delivery documents, customs forms, commercial invoices, and packing lists and extracts structured data automatically. Handles scanned paper documents, PDFs, and photos taken by drivers. Output populates your TMS, WMS, or ERP directly. Eliminates manual re-keying from documents and reduces data entry errors that cause billing and compliance problems downstream.

Load and warehouse slotting optimisation

Load optimisation models that maximise trailer utilisation by solving the 3D bin packing problem against your SKU dimensions and weight data. Warehouse slotting optimisation that analyses pick frequency, co-order patterns, and seasonal velocity to recommend slot assignments that reduce total pick travel distance. Both run against your operational data on a scheduled basis and produce actionable recommendations, not static rule sets.

Which logistics problem costs you the most right now?

Bring us the specific operational problem: late deliveries, forecast inaccuracy, excess carrier spend, or document processing time. We'll assess whether AI reduces it and what it costs to build.

Talk to our logistics AI team

AI for Logistics by area

Frequently asked questions

A demand forecasting model needs historical order or sales data, typically 18-36 months minimum, with enough granularity to detect seasonality and trend. Beyond the base demand history, the model improves significantly when you add external signals: promotional calendars (what promotions ran when), inventory availability history (was a stockout driven by demand or supply?), pricing history, and where relevant, external signals like weather data, economic indicators, or commodity prices. The model architecture we choose depends on the data you have. For most logistics and distribution businesses, a gradient boosting model or a temporal fusion transformer trained on your order history gives meaningfully better accuracy than a statistical forecast from a spreadsheet. We assess your data in discovery and tell you what accuracy improvement is realistic before we build.

Exception prediction is a classification problem. A model is trained on historical shipment data: shipments that completed on time, and shipments that experienced delays, damaged goods, missing documentation, or carrier failures. The model learns which combinations of signals, carrier, lane, origin-destination pair, time of year, weather conditions, shipment weight and dimensions, and days in transit, predict exceptions before they happen. At the point of booking or during in-transit monitoring, each shipment is scored. High-risk shipments are surfaced to your operations team with the contributing risk factors so they can intervene: hold alternatives ready, alert the customer proactively, or escalate with the carrier before the exception becomes a miss. The key difference from reactive tracking is that the alert comes before the delay is confirmed, not after.

Warehouse slotting is the assignment of SKUs to pick locations based on velocity, pick frequency, and co-order patterns. A poorly slotted warehouse has pickers travelling long distances for high-velocity items and fast-moving SKUs stored in inconvenient locations. Traditional slotting uses velocity-based rules: A, B, and C items by pick frequency. AI-based slotting adds co-order analysis, which identifies SKUs that are frequently picked together in the same order and places them near each other, and temporal patterns, which identify how velocity changes by day of week, month, or season. The output is a recommended slot assignment that reduces total pick distance and therefore pick time per order. For high-volume operations, slotting optimisation typically reduces pick travel distance by 15-30%. We build this as a model that runs against your WMS data on a scheduled basis and produces re-slot recommendations, not as a one-time exercise.

Standard TMS routing solves the vehicle routing problem using rules-based optimisation: minimise distance or time given a set of stops and vehicle constraints. This works well for predictable, static conditions. AI-based route optimisation adds two capabilities standard TMS tools lack. First, it incorporates real-time signals: live traffic conditions, weather, road incidents, and driver performance history. It re-optimises routes dynamically as conditions change, not just at the start of the day. Second, it learns from historical outcomes: which routes resulted in late deliveries, which drivers perform better on specific lane types, which stop sequences cause driver overtime. Over time, the model improves its routing quality because it learns from your specific operation rather than applying generic optimisation rules. For fleets running 50 or more routes per day, the combination of dynamic re-optimisation and learned performance patterns typically reduces fuel cost and late deliveries meaningfully. We scope the specific impact against your data during discovery.