Helping municipalities see where service delivery breaks
Public-sector data existed but was hard to act on. The work was building decision-support systems that gave municipal stakeholders operational visibility they could plan against.
The problem
Municipalities hold data relevant to performance, operational bottlenecks and service delivery, but it was not in a form that supported planning or day-to-day decisions.
Why it mattered
The customer was the public sector, so the value was public: better visibility of where service delivery was failing, and better-informed planning and resource allocation. That is legitimate impact even without a revenue figure attached.
The context
The Council for Scientific and Industrial Research, working in multidisciplinary teams combining software engineering, analytics and public-sector innovation.
What I did
I developed predictive analytics and operational intelligence systems supporting municipalities and public-sector decision making, and built Django-based decision-support systems serving 17 municipalities, including the City of Cape Town and 16 across Gauteng, enabling operational visibility and real-time access to analytics. I applied machine learning and data engineering to identify operational bottlenecks and improve service-delivery planning.
What changed
Municipal stakeholders could see operational issues and bottlenecks rather than infer them, which is the precondition for planning against them.
Who benefited
Municipal managers, planners and public-sector stakeholders across 17 municipalities, and indirectly the residents those services reach.
What remained
Decision-support systems in municipal use, and recognition for innovation in predictive modelling and enterprise solutions from the Mail & Guardian, the CSIR and the Department of Science and Technology.
Technical context
Python, Django, predictive analytics, machine learning, data engineering, operational intelligence dashboards.
Related
Turning environmental data into something people can use
Climate and environmental questions need satellite and geospatial data at petabyte scale, too large to treat as an ordinary dataset, and almost no organisation can process it alone.
TalkSession 5.8: How to use AI to learn a new skill - data analytics
A hands-on session showing how to use AI to learn data analytics from scratch — breaking down the learning process into practical, AI-assisted steps.
WorkUsing data to help students and a university decide
A university held a great deal of institutional data, but the questions that mattered for student success and planning were hard to answer from reporting alone.
WritingHow I Learned to Build My Own Python Libraries (From Curiosity to Real Work)
creating from 1st principles