BRIAN JABARIAN | Economics of Humans
BRIAN JABARIAN | Economics of Humans
I am a data scientist who likes to reduce complex phenomena to their essential principles. In my graduate studies in economics, I used statistical and experimental techniques to better understand how people make decisions, and I learned to communicate complex ideas to students and peers in the simplest terms possible. I want to use my skills to help answer the questions most pressing to individuals, organizations and society while constantly growing and exchanging knowledge with those around me.
For my capstone project at the General Assembly Data Science Immersive, I developed new modeling techniques to predict the outcomes of players' early games on online chess platform Lichess.org. My model uses chess engine evaluations and neural networks to achieve an additional 20% accuracy improvement upon Lichess's state-of-the-art model, and the techniques I employed can be used for better probabilistic predictions and matchmaking for new players.
A group project with Stanley Azuakola and Atigon Hongchumpol from the General Assembly Data Science Immersive. We developed a model that takes the geographic coordinates of a village in Africa and predicts whether that village suffers from extreme poverty. Our model uses publicly available satellite imagery along with convolutional neural networks and ensembling to catch 79% of cases of extreme poverty while maintaining an overall accuracy of 85%.
BRIAN JABARIAN | Economics of Humans
BRIAN JABARIAN | Economics of Humans