Noise Solution gains unprecedented live insights into their impact

The Challenge

Noise Solution helps vulnerable young people through the power of music and self-determination. As an award-winning third sector organization, they are always seeking innovative solutions to help maximize their positive impact. Sessions with their participants result in hours of video feedback and questionnaires that need detailed assessment. Manual processing was hugely time-consuming, unscalable and highly subjective, as the content was open to different interpretations. They needed an intelligent technology solution that could help them objectively and accurately analyze this massive quantity of unstructured data and revolutionize their work - and their impact.

The Wish

Noise Solution wanted a solution that would unlock the rich qualitative data within their video recordings. It would allow indications of participants’ wellbeing and sentiment to be surfaced in real time, as they progress through a program. It would enable better decision-making at every step - day by day and moment to moment. And it would also empower their young participants and the adults around them with more meaningful and immediate insights into their journeys.

The Solution

VRP Consulting devised a new solution whereby session participants’ spoken reflections on video are converted to text and analyzed with insights surfaced with the power of Tableau CRM. This would include determining the "next best action" that would maximize impact for the participant. To achieve this, video recordings and questionnaires from sessions would be gathered via VideoAsk and Appinium, then transcribed and sentiment analyzed via artificial intelligence models that VRP’s machine learning team created and deployed in Heroku. Finally, 360-degree insights would be provided via Tableau CRM and recommendations via Einstein Next Best Action.

The Stages

VRP always donate a proportion of their working hours as part of their Pledge 1% initiative and chose the Noise Solution idea as the perfect project to work on a fully pro bono basis. We set to work evaluating potential natural language processing (NLP) models in terms of performance, accuracy and cloud resources. During the prototyping phase, VRP tested Salesforce Einstein Language and intelligent APIs from cloud vendors such as Microsoft Azure, Amazon Web Services (AWS) and Google Cloud. Tableau CRM was ultimately chosen to enable very high levels of accuracy, performance and security.

With the analytics platform and model decided, VRP next built a proof of concept (PoC) using the chosen model. The results proved that purely from the data, it could accurately determine whether teenagers needed easier or more difficult sessions. Finally, VRP deployed the model into production, connecting it to real data feeds ready for a period of live learning and refinement of the model.

The Result

Noise Solution now has a powerful, secure and scalable platform that is capable of providing live evaluations of their impact and program participants’ wellbeing. It can help their team quickly and effectively find the best course of action as soon as a session finishes. The platform also empowers the young people to get a greater, more motivating sense of their own triumphs, with support and comments from adults whose opinions matter to them - and who can now play a closer role than ever before. And, in a sector that’s historically had difficulty demonstrating its impact, Noise Solution now has groundbreaking capabilities for telling its success stories vividly and persuasively using a wealth of both quantitative and qualitative data.

Company Profile

Noise Solution is a social enterprise that employs evidenced approaches to improving the wellbeing of vulnerable youth. Sessions involve pairing young people with music producers, and digitally capturing and safely sharing every participant’s journey within a safe, secure platform that performs like a social media platform. Each participant shares their music, achievements, thoughts and feelings about the process with family and keyworkers, who can then provide comments. This approach to digital youth work is multi-nationally award-winning and has been independently assessed as saving over a million pounds a year for local authority services and families across the East of England.