Using a standard data science approach; our teams used statistical analysis and algorithms to look for ‘markers’ and ‘patterns’ within the datasets that correlated with the key performance drivers for the tool we were developing.
Using machine learning to make better and faster decisions. From classifying text-based feedback, to assigning attrition prediction scores, to automatically allocating young people to the most suitable course.
Upskilling the team:
Engine focused on upskilling the newly formed NCS Advanced Analytics team. We had an ‘enablement’ workstream where we ran workshops and paired with NCS teams to upskill their team. This covered a wide syllabus from process through to adjacent areas such as Data Engineering and DevOps.
The tools Engine developed now sit within the NCS environment, producing outcomes in real-time for teams within NCS to make more timely decisions.
The attrition prediction tool assigns attrition prediction scores in real-time, allowing NCS decision makers early intervention on the journey from expression of interest to sign up.
Via the text analytics tool API daily feeds of texts and calls are categorised and fed back to Salesforce.
The auto-allocation tool acts as a “recommender“ for when a young person signed up. The tool automatically recommends them for the most suitable course based on fill levels, suitability, location, amongst other things. The tool has replaced a very time consuming and costly manual exercise for the NCS allocation team.