[02/02/24]Bayes Centre News: The Bayes Centre extends a warm welcome to ITER IDEA, its latest Member
The Bayes Centre is pleased to extend a warm welcome to its newest Member, ITER IDEA. This innovative company is focused on developing cloud-native services and AI productivity apps.
ITER IDEA envisions a world where resource planning is no longer a burden but is easy, effective, intelligent, and learns & grows with a business. The team assists customers towards authentic innovation with tailored solutions to increase the efficiency of existing workflows.
Its AIRP (AI-aided Resource Planner) platform will support manufacturing SMEs, healthcare units and public sectors remarkably low-tech to support their resource allocation and streamlining the assignment of tasks, especially in periods of staff reductions, high demand and uncertainty.
In this context, AIRP was selected as planning support by the Scottish Government Rural Payments and Inspections Division (RPID). Moreover, an assistant based on AIRP is under pilot for the scheduling of nurse rotations (82 resources) in the Emergency Department of the Baggiovara Hospital in Italy, forecasting a speed-up of over 60% compared to the previous system based on Excel and greater attention to respecting the hours limit and special requests of the healthcare personnel. In the healthcare sector, the lack of predictive support for hospital workforce scheduling has been identified as a major cause of clinician burnout in the UK and worldwide (Frost & Sullivan, 2022), (The Guardian, 2022); (ii) long waiting times are the main cause for public dissatisfaction with NHS services in the UK (69%), followed by perceived lack of staff (55%) (Statista, 2022); (iii) long waiting lists for dramatically impact countries adopting the Beveridge model with an average of 6 months for a Dermatological examination in Italy in 2019 (Statista, 2022).
In a nutshell, AIRP works as a pluggable service, delivering custom AI-aided strategies for users to solve resource planning with predictive scenario modeling. In particular, AIRP can integrate existing manufacturing execution systems (MES) and HR software to get data regarding resources, skills, planning, and machine cycles.
Through AIRP, the end-user accesses via browser a Gantt view from which they can monitor for example: overlaps of processes, employment of resources, pressure maps, respect for wishes and constraints on resources. predicted and actual demands.
The end-user can launch the algorithm, which will generate not only one single but up to 12 possible scenarios designed to solve the allocation while respecting the embedded parameters of its model (such as duration of shifts, skills, availability, etc.), but also parameters configured at runtime during the launch phase (e.g. usage objectives, grades and skills sought, allocation strategies, etc.).
In roughly 5 seconds, teams will know how AIRP could meet their demand, running What-if scenarios on their existing workforce and own data. By navigating the panel of generated scenarios, AIRP can show the end-users the people who have been suggested and who respect the constraints, information about factors that led to the prediction, constraints that cannot be met, and widgets to simulate the state of the slots after confirming the schedule. AIRP can integrate existing machine learning models and use them as predictive models to estimate distributions and support optimal schedule algorithms.
Visit ITER IDEA's website to find out more.