Context: Although vaccination rates have increased globally over the last twenty years — largely due to efforts to ensure vaccines are stocked at convenient points of care even in remote locations — they have plateaued in the last decade. This is largely attributable to children who drop out of their vaccination schedule, i.e., do not receive all their required vaccines, despite access. Delayed vaccination puts many children at risk and often requires costly vaccination campaigns to resolve.
Objective:
- predicting which children will not become fully vaccinated by 6 months
Solutions:
-
First through exploratory analysis, we were able to dig actionable insights from that data which will be beneficial to the organization to be able to build a better health supply system.
-
Using the map that shows different regions with the number of immunization drop outs, the organization is able to optimize the cost of allocation of health workers who attend to the patients.
- Through the model built, the organization is able to predict the patients who have not completed their doses of immunization and be able to allocate health workers to them.
Python 3.9
pipenv shell # Activating pipenv environment
pipenv install # Installing libraries in pipfile