How to predict everything - even who dies next in Game of Thrones

Machine Learning algorithms are routinely used to find hidden patterns in e.g. genomic data. But what if you used Machine Learning to get answers to questions that interest you personally? Guy Yachdav set out to ask the data something that was keeping him up at night: which of the characters in his favorite television series would die next? Guy worked with his colleagues, Dr. Tatyana Goldberg and Christian Dallago as well as a group of 40 students to develop a set of algorithms to predict, with surprising accuracy, which of the characters of Game of Thrones was likely to be killed off. In this talk, he shares their journey and the discoveries they made.

About Dr. Guy Yachdav

Dr. Guy Yachdav believes that data is the key to understanding and solving problems that affect every single aspect of our lives. Through the use of advanced algorithms and high-performance computing, he works on burning questions from a variety of domains. Whether you are interested in protein folding or who dies next on your favorite TV show, he believes that data can help you reveal the answer.

As a researcher, Guy worked with genomic data, developing software that helps scientists understand the way proteins carry out their function. He also created data analysis platforms that analyze the role of bacteria colonies in the digestive system, led an effort to create an open source biological data visualization tool, and built an online computational workflow that is used by tens of thousands of scientists.

Most recently, Guy led a project that helped popularize the field of data mining and machine learning. As a devoted fan of the “A Song of Ice and Fire” book series and its TV adaptation “Game of Thrones”, Guy recruited his JavaScript class of 40 students to build a website that (amongst other things) uses artificial intelligence to predict which of the hundreds of characters appearing in the narrative is most likely to die soon. The project has appeared in over 2.000 media outlets worldwide and has an estimated reach of 1.2 billion people.

As a technological entrepreneur, Guy founded several startup companies including Biosof LLC, a Columbia University spin-off that develops life science software and provides data science consulting services. The company has been awarded grants from the U.S. National Institute of Health and the U.S. Federal Health and Human Services.

Guy has a multidisciplinary academic background in the life sciences (PhD, Technical University of Munich, Germany), business (Executive MBA, Columbia Business School) and technology (BSc Computer Science, Columbia).