Publican AI — Ghana’s machine-learning customs enforcement at Tema Port

The Ghana Revenue Authority (GRA) deployed Publican AI at Tema Port, Ghana's primary import gateway, from 1 February 2026. The system uses machine-learning models to analyse import declarations and benchmark stated values against global trade price databases.

Publican AI is presented by GRA as decision-support technology: it assigns a risk score to each import declaration and flags anomalies for human review before shipment clearance, aiming to reduce valuation fraud and under-invoicing and speed up processing.

The system flags roughly 25% of declarations for additional scrutiny and is reported to have cut manual processing time from around two hours to about five minutes per declaration. GRA cites historical estimates of GH₵11 billion in annual revenue lost to valuation fraud and under-invoicing over 2020–2024 as the problem the system targets.

In its first weeks, GRA data showed monthly customs revenue rising from GH₵2.4 billion to GH₵3.6 billion, a near-50% increase attributed largely by GRA to improved import valuation. By April 2026, GRA claimed the system was generating roughly USD 3 million per day in additional revenue.

Independent analysts have publicly questioned whether the revenue surge is causally attributable to the AI system rather than other enforcement factors, calling the evidence too early to verify and requesting a formal independent audit, which had not been completed as of June 2026. Traders report they cannot understand how customs values are determined, disputes are escalated to a secretariat meeting only twice weekly, and no algorithmic transparency has been published. The Ministry of Finance convened a multi-party technical committee in April 2026 in response. This is an early-stage deployment with promising but contested results and documented governance gaps, not yet a verified success.