Women’s Health Risk Assessment – 1st Prize Predictive Experiment

This is the winning solution for the Women’s Health Risk Assessment data science competition on Microsoft’s Cortana Intelligence platform. In this page you can find the published Azure ML Studio experiment of the most successful submission to the competition, a detailed description of the methods used, and links to code and references. The competition To help achieve the goal of improving women's reproductive health outcomes in underdeveloped regions, this competition calls for optimized machine learning solutions so that a patient can be accurately categorized into different health risk segments and subgroups. More specifically, the objective of this competition is to build machine learning models to assign a young woman subject (15-30 years old) in one of the 9 underdeveloped regions into a risk segment, and a subgroup within the segment. After the accurate assignments of the risk segment and subgroup in each region, healthcare practitioners can deliver services to prevent the subjects from sexual and reproductive health risks (like HIV infections). The types of services are personalized, based on the risk segment and subgroup assignments; such customized programs have a better chance to help reduce the reproductive health risk of patients. A summary and more detailed description of the competition are available here: https://gallery.cortanaintelligence.com/Competition/Women-s-Health-Risk-Assessment-1 The scripts used in R Studio and in ML Studio to produce and use the successful model uploaded in Azure ML Studio can be found here: https://github.com/IonKl/Womens-Health-Risk-Assessment-Competition The local R script that generated the model is in https://github.com/IonKl/Womens-Health-Risk-Assessment-Competition/blob/master/WHRA_Onprem_XGBoost.R