We take many things for granted in our lives: air-travel, advanced health care, and lately, realtime information such as the cheapest airfare available. A data-driven application such as the latter is made viable by the unprecedented growth of electronic data. However, manual analysis of a large dataset is cumbersome, error-prone, and impractical in many situations. It is the automatic methods, supported by advanced machine learning and data-mining algorithms fueled the accelerated growth of data-driven applications recently.

The primary motivation of my research is to discover novel approaches to automatically recognize patterns in large datasets and develop tools to answer questions that affect people. Upon noting that most of the collected data is still unanalyzed and under utilized, even with the availability of powerful tools, I am primarily motivated by how useful inferences can be made with little extra effort on the data that is already available. In this context, I am working on problems in medicine, systemic risk in financial systems, and sports. My masters’ thesis focused on methods to improve the quality of multi-parameter physiological signal data in realtime. Going forward, I intend to work on learning predictors for global systemic risk using financial data such as consumer spending, security lending, etc.

My career goal is to become a leading authority in data-driven applications. Upon completing my doctoral work, I plan to join an R&D initiative either in academia or industry. I am particularly interested in balancing the need for application specific solutions and the desire for data agnostic methods that will be useful across heterogeneous domains.

I came to MIT driven by my desire to develop solutions that affect people globally, and propelled by the exposure from participating in two Google Summer of Code programs, where I had the unique opportunity to work with people from around the world. Few years later, I am jaded. Although, the Stata center is the home of many forerunners who are defining our future in technology, I often find myself trapped in my research and bounded by the invisible boundary of the Stata center.

Interaction with researchers from diverse backgrounds and fields will give me an invaluable opportunity to identify the interesting problems in different areas. Further, this will let me obtain a grassroots perspective on how data mining could be better used in the respective areas. Through Global Fellows Program, I hoping to develop contacts and build collaborations with other researchers. This will assist me in furthering my career goal of expanding machine learning methods to wide range of areas yet untouched, transfer methods proven to work in one area to another, and provide integrated data-driven solutions to multiple problems.