Malaria Commodities Prediction

An Application of Time Series Analysis

Abstract

Background: The WHO Global Malaria Programme is responsible for coordinating WHO's global efforts to control and eliminate malaria. Resultantly, Kenya is aiming at making significant strides towards the elimination of malaria, with the implementation of several interventions targeted at regions of the country. Problem: Tracking and restocking of Malaria commodities is currently done on the basis of 6-month averages computed by MoH officials from the KHIS system data. The averages utilized are not efficient in projecting a clear and desired picture of trends related to consumption such as seasonality, increases or decreases as well as other confounding factors. Objective: Consequently, this project serves the purpose of  creating a time analysis predictive model that is able to monitor common patterns and trends and give our projections of what is expected as per areas of low demand and areas of high demand in order to have efficient restocking of Malaria commodities as per the needs of KHIS. Methodology: Data was derived from the KHIS System as a CSV file. Pandas was used to perform data wrangling and model the time series data. Furthermore, to generate the predictions, the gradient boosting regressor algorithm was used to create actionable insights forecasting quantity of commodities that would be required per county; with an evaluation of the model’s performance being done using RMSE. Results: The model evaluation using RMSE showed a result of 28 unveiling a fair performance for the model applied to the time series model. Conclusion: Based on the performance of the model applied on the time series data, it promises significant regularization hence its potential for use in determining malarial commodities required. Recommendations: The project widely affects the impact of the distribution of malarial products hence future work will involve incorporating a live map of Kenya to easily identify counties being affected.