Retail Metrics

Honey Access AI software

Challenge

Honey Access runs 4000 sensors worldwide collecting Wi-Fi and Bluetooth signals from devices such as smartphones which people carry, hands-free car-kits installed in vehicles, bluetooth-enabled speed sensors in bikes and many more, delivering over 10GB of data per day.

Thanks to the fact that each device has its unique ID, the technology is able to determine how people move from A to B and how long they stay in a particular location. However, GPS doesn’t work indoors. What you have indoor is e.g. Wi-Fi signal sent out from smartphones. Classical indoor GPS-like triangulation mathematical formula doesn’t offer enough accuracy. Signals bounce off the walls.

Solution

A machine learning algorithm which determines position not using mathematical formulas, but a purely practical approach: for each spot inside a venue it learns about signal strength characteristics. Any bouncing signals are not a problem (as in classic formula - based approach) but actually help to better estimate position of a person.

Result

Rough Proof-of-Concept development time: 2 weeks. Full AI Solution development time: 8 weeks (including the online GUI for calibration). We received a super-fast data processing system within months, rather than years (as we would probably end up using frameworks like Java/Spring).

Our Responsibilities

Web Development

UX/UI Design

Tech Stack

Visual Data Presentation

Finding way through the maze of metrics

There is a huge amount of data collected and presented to users. How to avoid overwhelming them? This was the task of the Visla team: to design the app in a way it attracts and shows clearly the most important metrics.

Fighting traffic jams with beautiful maps

Honey Access app provides municipalities important insights into traffic patterns in their cities. Like how do people move from A to B and how much time does it typically take. There’s a ton of ways you can present these things. Visla UX team goal was to make this information as clear as possible to the end user.

Raw data and advanced mining

Social Wi-Fi

Why give Wi-Fi for free if you can get your customer’s phone or e-mail in return? Thanks to cooperation with Socialwave, a social Wi-Fi solution provider, our solution can be used not only for tracking and analytics but also as a Wi-Fi hotspot, which connects with users over Facebook, WhatsApp or e-mail.