Cristina is a recent MIT graduate with background in quantitative social science. Over the past five years Cristina has been involved in various experimental and quasi experimental research projects inside academia and as part of program evaluation work in the non-profit sector, most recently through the Abdul Latif Jameel Poverty Action Lab. During her studies at MIT, Cristina focused on political economy and quantitative methods, taking a strong interest in causal inference, statistical modeling and a career in data science. At NYCDSA, she used supervised machine learning algorithms and ensemble methods to predict the magnitude of insurance claim losses and built a collaborative filtering based movie recommendation system using Python and Spark.
Introduction In October 2016, Allstate launched a Kaggle competition challenging competitors to predict the severity of insurance claims on the basis of 131 different variables. Better […]
Past occurrences can serve as a useful guide shedding light on trends and informing future decisions. In this blog post, I present an interactive application that leverages 911 […]
Join our community with 10,000+ data-passionate members and keep yourself posted on the latest news and events of the data science world.