evidoria

← Back to browse

Good practice Imported

Pronto — Port of Rotterdam Authority's AI-Assisted Port Call Optimisation Platform

Netherlands · Rotterdam · See the Netherlands profile · See the Rotterdam profile

Evidence: Observational / pre–post Top 22% 73/100 · Ask Evidence Copilot about this practice

Since 2018, the Port of Rotterdam Authority's Pronto platform has used AI-driven arrival predictions to coordinate port calls, cutting vessel waiting times by up to 20% and reaching adoption by nearly half of the port's shipping companies and terminals.

up to 20 %
Vessel waiting-time reduction (since 2018 pilot)
almost half share of active companies
Adoption among port shipping companies, agents and terminals (2025)
~30,000 vessel calls/year
Annual vessel calls covered (2025)

Details

Maturity
Established
Promoter
Port of Rotterdam Authority
Period
2018–present
Region (NUTS)
NL33
Keywords
maritime, ports and logistics, transport, supply chain

Context

Since April 2018 the Port of Rotterdam Authority, working with IT partner BIT, has run Pronto, a joint data-sharing and machine-learning platform predicting vessel arrival and departure times and coordinating bunkering, servicing and berth planning for around 30,000 vessel calls a year.

Objectives

Pronto aims to cut vessel waiting times and improve coordination between shipping lines, agents, terminals and the Harbour Master through AI-driven arrival predictions and shared planning data.

Activities

A self-learning model trained on AIS tracking data, vessel-visit history and weather information supports joint port-call planning; the approach has since evolved into the wider PortXchange product used beyond Rotterdam.

Results

Maritime trade press reported waiting-time reductions of up to 20% following the pilot, corroborated by an on-record quote from Shell's shipping GM; by the port authority's own account, almost half of the shipping companies, agents, terminals and other nautical service providers active in the port now use the platform.

Conclusions

The Port Authority's own 2025 Digital Report is candid that a newer fairway-traffic-planning module still struggles to predict departure times from open-source data and that its gains are still being quantified, so not every part of the Pronto/PortXchange family is equally proven.

Implementation
Indicative cost
High (€500k–€5M)
Time to results
Long (> 3 years)

Commonly funded by

Own resources / municipal budget

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful