Ralixar

Visibility and exceptions

ML Prediction

Predictive ETA and Visibility

Carrier, terminal, customs and surface milestones arrive with different names, timing and completeness. A published schedule alone cannot explain current arrival, dwell or hand-off risk. Ralixar keeps model assistance behind confidence gates and authorised review.

GOVERNANCE

Confidence-gated intelligence

Stale, contradictory or sparse events lower confidence and surface a review state; forecasts never overwrite confirmed milestones.

The problem

Disconnected evidence creates avoidable review work.

Carrier, terminal, customs and surface milestones arrive with different names, timing and completeness. A published schedule alone cannot explain current arrival, dwell or hand-off risk.

One timeline

Carrier, port, customs and partner events are normalised

Governed workflow design

Freshness shown

Every prediction states when its inputs were last observed

Governed workflow design

Rules continue

Confirmed events remain the system of record

Governed workflow design

The AI under the hood

A named technique behind an explicit control boundary.

The model has a bounded job. It does not own the workflow or decide what a person must do.

ML Prediction

Technique in plain English

Time-to-event and sequence models estimate arrival and dwell from current milestones, route history and operating context.

Inputs

  • Planned route and carrier schedule
  • Observed carrier, port and customs events
  • AIS or surface movement signals where available
  • Historical lane, terminal and dwell patterns

Confidence gate

Stale, contradictory or sparse events lower confidence and surface a review state; forecasts never overwrite confirmed milestones.

Rules fallback

Published schedules, confirmed events and deterministic lateness thresholds continue to drive the timeline when prediction is unavailable.

What the human decides

An operator accepts operational changes, communicates commitments and instructs carriers, CHAs, warehouses or transporters.

Evidence and expected outcomes

Industry evidence, not invented product proof.

Each item states its source class and boundary. Ralixar is pre-launch; these figures do not claim customer outcomes.

Modules involved

One workflow across a shared shipment record.

Each module works on the same evidence, event and decision history.

Related solutions

Continue through the same operating record.

Demurrage and Detention Prevention

Connect forecasts to free-time exposure.

ML Prediction
Learn more

Route and Drayage Optimisation

Re-plan feasible movement options.

Optimisation
Learn more

Conversational Analytics

Ask governed questions of milestone performance.

LLM Single-shot
Learn more

Review predictive eta and visibility on your own shipment flow.