[MUSIC] Hello, and welcome. My name is Dimitri, and I'm happy to see you are interested
in competitive data science. Data science is all about
machine learning applications. And in data science, like everywhere else,
people are looking for the very best solutions to their problems. They're looking for the models that
have the best predictive capabilities, the models that make as
few mistakes as possible. And the competition for one becomes
an essential way to find such solutions. Competing for the prize,
participants push through the limits, come up with novel ideas. Companies organize data science
competitions to get top quality models for not so high price. And for data scientists,
competitions become a truly unique opportunity to learn, well,
and of course win a prize. This course is a chance for you to catch
up on the trends in competitive data science and learn what we,
competition addicts and at the same time, lecturers of this course,
have already learned while competing. In this course, we will go through
competition solving process step by step and tell you about exploratory data
analysis, basic and advanced feature generation and preprocessing,
various model validation techniques. Data leakages, competition's metric
optimization, model ensembling, and hyperparameter tuning. We've put together all our experience and
created this course for you. We've also designed quizzes and programming assignments to let you
apply your newly acquired skills. Moreover, as a final project, you will
have an opportunity to compete with other students and
participate in a special competition, hosted on the world's largest platform for
data science challenges called Kaggle. Now, let's meet other lecturers and
get started.