FindExporters

Identifying UK companies with highest export potential using propensity scoring

  • Publicly sourced

The challenge

DBT staff needed to manually sift through millions of UK companies to identify export potential and make subjective decisions about which companies to engage first. This created inefficiencies in resource allocation and made it difficult to target export support services effectively.

The solution

FindExporters uses a LightGBM Classification Model to predict the probability that a company will export within the next 6 months. The system processes data from Companies House, DBT internal databases, and HMRC export records to generate export propensity scores on a 0-1 scale. Companies are categorised into five risk levels from "Very High" to "Very Low" export potential, enabling DBT staff to make data-driven decisions about which organisations to engage first and allocate resources more effectively.

The results

FindExporters is currently operational, processing millions of UK companies daily with an average of 0.143 daily users among DBT staff. The system has replaced manual, subjective company identification with data-driven probability scoring, enabling targeted allocation of export support resources to high-potential companies. The tool provides systematic coverage of all UK companies and supports informed decision-making about business engagement.

Details

Organisation name
Department for Business and Trade (DBT)
Government body
UK Government
User group
Civil servants
Use case type
Specific
Type of technology
Machine Learning
Phase
Live
Impact
Improved efficiency / Time savings

Links

Get in touch

Email ai-knowledge-hub@dsit.gov.uk to:

  • find out how to use or collaborate on this tool
  • review content for this tool
  • talk to us about your own tool

Content created: 25 September 2025