Sina Sanjari

I am a data scientist with more than seven years of experience in problem-solving in data science, machine learning, artificial intelligence, statistical modeling, optimization, and quantitative analysis. I have a strong background in data science, financial mathematics, statistical modeling, market design, and machine learning, also in related algorithms, mathematical tools, and programming languages.

 I worked in the National Research Council Canada as a data scientist, where I developed algorithms and statistical models to learn infection propagation patterns in water distribution systems. I have used the combination of actual and simulated data, representing the propagation of dangerous chemicals in the network to predict the source/region of infection. I have implemented algorithms using Python, TensorFlow, PyTorch, C++, and Linux.   

I received my Ph.D. in mathematics and statistic from Queen's University and I have two years of experience working as a machine learning researcher at the University of Illinois Urbana-Champaign. My research has been focused on decision-making under uncertainty. The main question is to understand how a collection of decision makers (human/artificial agents) can make optimal or satisfactory decisions using data in the presence of uncertainty in the environment or the underlying unknown model. An application of these models is in energy and financial markets, where multiple distributed renewable energy stations or financial firms compete for optimal energy production or investment and pricing policies, where an abundance of energy resources or investments might lead to price fluctuation, creating an incentive to interact strategically. I characterized the properties of the optimal solutions and designed several algorithms that lead data-driven decision-makers to attain satisfactory or optimal performance. I have published my research in several data science and machine learning journals and conferences.

I received my Ph.D. in mathematics and statistic from Queen's University working on machine learning, decision theory, and statistical learning.