Hoxton Convert

Measure your in-store conversion rates

Advanced people count sensors and seamless integration with POS. Identify gaps in your conversion, and close them.

From £720 / $995 / €900 per store per year

Book a demo

HoxtonAi is trusted by thousands of users:

Store performance

Track top performers and spread the skills

Rank your conversion performance by store or sales team - and get everyone else ready to learn from the best. Our customers have seen up to 20% revenue uplift through tracking and training on what works.

Marketing effectiveness

Measure what works

Is your marketing effort driving traffic to the store, and is that new traffic converting into sales? Foot traffic and conversion can clear up which marketing dollar made sense, and which didn't.

Portfolio analysis

Group sites by data not by intuition.

Data on one store is good. Data on many stores is a gold mine. Understand the differences in traffic and conversion in city-centre, out-of-town, roadside and seaside. Segmenting your stores by patterns in performance can provide essential insights on what will work - where.

Sensors, integrations and software all in one package.

User access management

Manage whether a user has Admin access or access to the data of just one or a subset of stores. Maintain data security and provenance from the store manager to the portfolio to the global HQ.

Sensor setup wizard

HoxtonAi's setup wizard takes you through the install process step-by-step. With just a 15-minute setup, you'll leave plenty of time to do what matters - spend time with your customers, not your suppliers.

Accuracy and audit

With count accuracy of over 98%, the Hoxton sensor won't let you down. Unlike infrared technologies, we use the latest AI algorithms for both privacy purposes and counting accuracy.

Why 98%+ accuracy

Counting based on journey prediction, not simple line crossings

Most people counters fire a +1 the instant something crosses a beam or line. That's fast — but it's also why they overcount. Hoxton works differently: it uses an overhead view to recognise a complete in-view journey and only counts when the journey matches a real entry or exit.