Vitality Hub specialise in senior holistic health and offer a range of services including clinical exercise/personal training (private or corporate), group fitness classes, well-being and programmes for people with clinical health limitations. They gained academic expertise from the University of Kent to identify a machine learning algorithm that could automate the grouping of Mature Movers clients to design personalised programmes for them.
The Challenge
Vitality Hub’s ‘Mature Movers’ programme specialises in fitness for people aged over 65, and involves working with individuals in their homes or within the residential and nursing care home industry. They saw immense growth over 2020/2021 and reached full capacity. In order to help more people, the business needed to build a system which would automate the grouping of people to designed personalised programmes. They wanted to investigate the potential for applying machine learning algorithms to data collected from the ‘Mature Movers’ physical health, exercise and wellbeing programme, so that they could scale the business further.
The Approach
With support from EIRA’s Innovation Voucher scheme, academics from the School of Computing worked with Vitality Hub on a unique project, to develop a machine learning approach which would allow for participants’ personal preferences and health requirements to be taken into consideration, when establishing the participants’ exercise routines.
Professor Alex Freitas led the project. The biggest challenge was that the company had minimal data that could be used effectively for machine learning. Therefore, the project’s focus changed to establishing the most effective means of gathering data, suitable for use with a machine learning algorithm. The type of attributes collected needed careful consideration to avoid unexpected bias. Prof Freitas reviewed the existing data, in terms of personal health and fitness profile, making recommendations on how the existing questionnaire could be improved with more closed, granular questions that are better suited to analysis by machine learning.
The next challenge for Professor Freitas was to select a suitable machine learning algorithm which would work with the type of data available and achieve the desired prediction, coupled with the decision of whether to adopt supervised or unsupervised learning.
The Outcome
Professor Freitas and his team produced a report which recommended a method for data collection and the type of data and attributes which should be collected. They gave advice on the collection, storage and pre-processing of the data, and finally recommended a machine learning algorithm to use. They suggested Vitality Hub use “Decision Trees”, a well-known machine learning data science technique for predictive modelling which have advantages over some other algorithms as they are efficient and their construction is comprehensible so the decisions can be examined and understood.
“This research provided the foundations for business vision and scalability options. The collaboration has brought about traction in the industry and unforeseen opportunity.”
Rosaria Barreto, Director at Vitality Hub
Next Steps
The long-term goal would be to build on the outcomes of the project. The company are seeking further support to develop the software and enable the collection of the data via questionnaire to assess individuals’ needs and then stream them into the most suitable exercise scheme, depending on this data using the machine learning algorithm. Rosaria Barreto, Director of Vitality Hub has been accepted on the Young Global Innovators Programme (Innovate UK) and the business is waiting on funding confirmation from other grants.