NAB Yourself is an interactive web experience designed for self‑reflection, helping people start thinking about what they really want in life.
Combining facial analysis and speech recognition, people could scan their face and answer prompts designed to spark a conversation. While answering, the web application analysed what they said and extracted key themes.
By the end, people received a one‑of‑a‑kind artistic representation of themselves — a unique visualisation of their ambitions, transformed into art through technology.
My role
As Technical Director, my role involved:
- Liaise with both internal and external stakeholders to help with creative, scoping, prototyping and client presentations.
- Design and prototype around feasibility and creative execution — pushing the boundaries of what was achievable technically, all in the browser.
- Lead a team of x3 developers and a tester to build, test and deploy the project under a super tight production timeline.
- Lay the foundations for core biometric analysis, speech recognition analysis, and real‑time artistic illustration generation.
Key results
- Customers spent an average of 4.25 minutes talking to themselves, with 4 out of 5 users interviewed saying the experience had a positive impact on thinking about what they really wanted in life.
- 41,343 data points generated, allowing the National Australia Bank to connect customers with products tailored to them.
Technology
Biometric analysis was built on Amazon Rekognition plus a set of custom algorithms, enabling us to extract key face metrics, balance results based on facial expressions, and transform property ratios to align with creative direction.
Speech analysis used both the native Web Speech API and IBM Watson to convert speech into transcripts. We then analysed text in real time using natural language processing to extract themes and metrics, transforming what each person said into animated illustrations. Symbols, shapes, positions, and colours that filled different parts of the illustrated faces were driven by voice data.
Working with a national bank meant high standards around security, accessibility, and browser support. To make the experience fully AA accessible and support Internet Explorer 11, we had to get creative. For example, we developed a bespoke feature fallback (based on Adobe Flash Player) for browsers that didn’t support the MediaDevices interface. We also optimised performance to run real‑time analysis and animation smoothly across a wide range of devices.