Preparing for Kaggle Competitions
Details
Please RSVP using Eventbrite for an accurate head count as space is VERY limited!
Description
Kaggle was founded in 2010 as a platform for predictive modeling and analytics competitions on which companies and researchers post their data and statisticians and data miners from all over the world compete to produce the best models. This crowdsourcing approach relies on the fact that there are countless strategies that can be applied to any predictive modeling task and it is impossible to know at the outset which technique or analyst will be most effective. Kaggle also hosts recruiting competitions in which data scientists compete for a chance to interview at leading data science companies like Facebook, Winton Capital, and Walmart.
At this meetup, you will learn more about the Kaggle community and how Kaggle competitions work. Kaggle has run over 200 data science competitions since the company was founded. It is best known as the platform hosting the $3 million Heritage Health Prize.
Competitions have resulted in many successful projects including furthering the state of the art in HIV research, chess ratings, and traffic forecasting. Several academic papers have been published on the basis of findings made in Kaggle competitions. A key to this is the effect of the live leaderboard, which encourages participants to continue innovating beyond existing best practice. The winning methods are frequently written up on the Kaggle blog.
Agenda
• How to participate in a Kaggle contest ("Top Kaggler Secrets Revealed"), as well as how to host a competition (why you should host, what to expect, etc)
• Reviewing simple case studies and competitions: Titanic ( https://www.kaggle.com/c/titanic ) & Digit Recognizer - ( https://www.kaggle.com/c/digit-recognizer )
• Workflow reproducibility, model and feature selection, and running on EC2
• Reviewing simple competitions: Titanic (https://www.kaggle.com/c/titanic) & Digit Recognizer -(https://www.kaggle.com/c/digit-recognizer)
Who should attend
Everyone! The goal is to eventually compete in a competition.
Pre-requisites
Programming language basics, Machine learning algorithms and its implementation, previous Kaggle datasets.
Meet your Speaker
Micah Brown (https://www.linkedin.com/in/micahbrown1) is the CEO and Founder at Centiment. He has worked as a senior level technology consultant and manager within the insurance industry for Aon as well as in commercial, retail and investment banking at Barclays and within media technology for Viacom and NBC. He specializes in applied artificial intelligence from a product perspective and is currently working on a PhD in experimental psychology, mixing machine learning and AI from a theoretical and practical perspective and using the power of both of those tools to understand people's behaviour in relation to digital media - with a specific focus on semantic analysis based feature space reduction.
About our Sponsors
Galvanize is an education company that blends the lines between learning and working. We believe in creating easy access for anyone who has the drive and determination to jump into the tech world, especially in entrepreneurship, engineering, and data science. Our campuses are home to students, startups, investors, mentors, and other people who are engaged and excited to level up their skills. To learn more about Galvanize, visit galvanize.com.
At Centiment, what helps us stay so focused and motivated is the desire we have to inject human emotion and personality back into advertising and tackle one of the biggest problems facing the industry: Serving irrelevant ads and content to the wrong audience at the wrong time.
https://a248.e.akamai.net/secure.meetupstatic.com/photos/event/7/9/7/3/600_457591091.jpeg
https://a248.e.akamai.net/secure.meetupstatic.com/photos/event/2/2/4/f/600_452528783.jpeg