School of Business
Reimagining workforce planning and staff retention through AI and data analytics powered OSI model
The NHS staff shortage has been at the front and centre of the 2024 elections. However, simply hiring new staff is insufficient, given the lengthy training pathways and the limited pool of international recruits. Sustaining or increasing overall staff numbers is impossible without retaining current employees and their valuable skills and experience, making retention critical for a well-functioning NHS and organisations generally. We have developed a novel AI and data analytics-powered Organisation Self Identification (OSI) model that supports organisations to understand how to manage proactively and, where possible, reduce the occurrence of staff turnover. Our solutions help significantly reduce staff turnover intention and improve the overall functioning of organisations, which are, more significantly, within management's ability to implement.
Understanding OSI
OSI is displayed through solidarity behaviours at three levels – commitment (through self-efficacy behaviour), engagement (self-value), and empowerment (employee voice) (Pepple, 2020). We define self-efficacy as staff's need to have control over their job. while self-value underpins the notion that working in an organisation serves as a means of self-identity because of the value staff place on their organisation. Employee voice explains the need for staff to take ownership of their jobs to the extent that they invest themselves in their organisation and come to intimately understand its vision and mission (Peng & Pierce, 2015). Investigating Turnover intention is critical because it is the withdrawal process in which a staff begins to think about leaving their job (Pepple et al., 2021).
Our service offers
Our AI and data analytics-powered OSI model is novel and can do the following:
- Identify the root causes of staff turnover, both intention and actual, at the organisation, department, and unit levels.
- Predict the department, units and team at risk of staff turnover intention and actual turnover and the key issues specific to them
- The OSI status at an organisation, department and unit levels and the predictors impacting them
- Support the prescription of bespoke intervention for addressing staff turnover intention and actual turnover.
- Audit the extent to which workforce policies support OSI to foster employees’ efficacy, voice, and self-value using our bespoke AI-powered OSI sentiment analysis tool.
Our method
Our method involves reimagining the available workforce data, including staff surveys through data analytics and AI to identify OSI dimensions’ variables and their predictors. We have also developed a bespoke AI-powered sentiment analysis with our OSI model, which allows organisations to review and improve their workforce policies such that it fosters OSI sentiments.
Organisation partners
We are currently working in partnership with the University Hospitals of Leicester and are grateful to the Trust's leadership for taking the lead in this area.
Events
At our stakeholder events, we updated the Leicester Royal Infirmary and Glenfield Hospital, we updated staff and leaders on our work's progress in addressing staff turnover intention through our AI and data analytics-powered Organisation Self Identification (OSI) model. Our presentation highlighted core issues underpinning the root causes of high staff turnover intention and actual turnover in the Trust and the progress made in this area. We have successfully audited 14 workforce policies, enhancing workforce policy development practice by ensuring that workforce policies support OSI. This process has achieved significant improvements in safe staffing and non-medical e-rostering policies.
Testimonials
“This is an excellent example of collaborative working practice between institutions in Leicester. We are proud to be able to support this project. Our aim is to use innovative approaches to support the workforce, which in turn will benefit the care we deliver to our population."
Assistant Chief Nurse, Antonella Ghezzi, added: University Hospitals of Leicester
I am so pleased to see progress in the right direction. I am absolutely honoured to be considered by yourself as a trailblazer in this field.
Lead Nurse, safe staffing comment following improved non-medical e-rostering policy, University Hospitals of Leicester
Our funders
The Leicester Institute for Advanced Studies (LIAS)
ESRC Impact Acceleration Account
Project team
Dr Dennis Pepple - Project Lead, University of Leicester- Dr Aliyu Sambo - Data Analytics Lead
- Antonella Ghezzi - Assistant Chief Nurse and University Hospitals of Leicester Project Lead
- Professor Nigel Brunskill - Director LHAP
- Professor Tim Coats - Professor
- Dr Godbless Akaighe - Work Psychology Researcher
- Dr Wen Wang - Work Psychologist
- Dr Charles Ambiluchi - Data Scientist
- Dr Ejike Roberst - Data Scientist
- Jo Wilcox - Lead Nurse Simulator
- Ololade George-Aremu - PhD Researcher
- Leila Masooni - Research Assistant
Contact
For information about the project please contact Dr Dennis Pepple