unthinkable
Case study · A maritime research firm, London, UK · freight intelligence

The firm's subscribers get ocean freight benchmarks in hours instead of 7-8 days, and see the cheapest routes between ports.

The firm, founded in 1970 and trusted by over 3,000 clients in 100+ countries, wanted the shippers and forwarders who subscribe to know a fair freight rate quickly, so they could cut costs and decide in time.

London, United KingdomFleet & logistics (transport, dispatch, analytics)

What changed

20xfaster freight costing calculations (as reported)
2Xfaster decision making (as reported)
30%less data redundancy (as reported)
What stood in the way

What stood in the way.

What stood in the way
  • Processing rate data from hundreds of shippers and forwarders took the portal a very long time, so insight arrived late.
  • Bad data points were hard to find and remove, which weakened the benchmarks.
What changed
  • 20xfaster freight costing calculations (as reported)
  • 2Xfaster decision making (as reported)
  • 30%less data redundancy (as reported)
What we built

What we built.

  • Python ETL pipelines, run on Airflow and Kubernetes, behind a Laravel web app.
  • Benchmarks from long-term contract rates and short-term spot rates in hours instead of 7-8 days, and outlier checks in minutes instead of 1-2 days.
  • Duplicate checks and bad-data reports that point to the exact cell with the wrong value.
  • Route comparison across ports, clusters, countries and regions, showing the cheapest route and the highest, lowest and average rates in charts.
  • A market overview searchable by port, container type, size of goods and shipping months, with analyst appraisals by container type, region and port.
  • Laravel
  • Python ETL pipelines
  • Apache Airflow
  • Kubernetes
What it shows

What this work shows about us.

We know what a shipper is asking

What is a fair rate on my lane, and is there a cheaper route? The portal answers both from the same benchmark.

Fix the data, then the speed

Clean data and pipelines turned a week of processing into hours without changing what the analysts publish.

Want to rebuild your freight intelligence portal like this? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.

Start your plan ↗
If we built it today

If we built it today, with AI.

This work came before today's AI. If the London-based maritime research firm asked us now, this is what we would add, step by step.

Quote

An agent would answer a subscriber's rate question for a lane from the latest benchmark, with the cheapest route and its port charges. Analysts still set the appraisals.

Tracking

An agent would watch each week's benchmark and tell a subscriber when rates on their lanes move, and check incoming rate files, asking the sender to fix bad cells before the run.

Ask Unthinkable

Want this for your business?

Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.

Send us a note instead

Required

Thanks. A senior AI engineer will reply to you.
u
Ask UnthinkableClarity first, then the right team
Your conversation

An AI agent. This prototype uses prepared answers and sends nothing.