In this project, we analyzed the infant mortality data from Center for Disease Control and Prevention (CDC) and desigend a framework to

1. Evaluate the risk of infant death
2. Provide reference to similar pregnency cases in tha past to help the doctors in taking informed decisions.

Data Link: CDC Data

Methods Used:

1. Spark for Data Processing
2. Dimensionality Reduction to reduce the number of features
3. Similary Search and Clustering to find the similar pregncnecy cases happened in the pas
4. Machine Learning to evalute the risk of new infant death

For complete details refer Report

Team

Anurag Arora

Keshav Gupta

Renu Rani

Shayan Ray