Model Shootout: Comparing Linear Models, Trees and Neural Networks for Binary Classification by Jared P. Lander
Visit [ Ссылка ] to learn more.
Abstract: When analyzing data there are so many different kinds of models to choose from. Generalized linear models, tree-based models, neural networks, ensembles of all these. For a given problem set, we'll compare a number of differrent models and see which did best, to find the pareto optimum of performance and speed.
Bio: Jared P. Lander is Chief Data Scientist of Lander Analytics, the Organizer of the New York Open Statistical Programming Meetup and the New York R and Government & Public Sector R Conferences, an Adjunct Professor at Columbia Business School, and a Visiting Lecturer at Princeton University. With a masters from Columbia University in statistics and a bachelors from Muhlenberg College in mathematics, he has experience in both academic research and industry. Jared oversees the long-term direction of the company and acts as Lead Data Scientist, researching the best strategy, models and algorithms for modern data needs. This is in addition to his client-facing consulting and training. He specializes in data management, multilevel models, machine learning, generalized linear models, visualization and statistical computing. He is the author of R for Everyone (now in its second edition), a book about R Programming geared toward Data Scientists and Non-Statisticians alike. The book is available from Amazon, Barnes & Noble and InformIT. The material is drawn from the classes he teaches at Columbia and is incorporated into his corporate training. Very active in the data community, Jared is a frequent speaker at conferences, universities and meetups around the world. He's an R Consortium Board Member. His writings on statistics can be found at jaredlander.com.
Twitter: [ Ссылка ]
Presented at the 2023 D4 Conference (August 24, 2023)
