On June 1st, 2016, Kenshoo with the support of AWS will be hosting our first ever public Data Hackathon! This Hackathon is a chance to prove your Big Data + Analysis skills by solving a real-world problem over huge real-world datasets.
The problem: We are interested in predicting the “money in the funnel” problem. Given a path of historical user events (clicks and conversions), one should try to predict the future revenue potential that is expected for the user.
The goal: We will chop off the last days of the event stream. The winning team will be the one who will be able to most accurately predict the value of the conversions that were chopped off.
The data set: 50 TB of anonymized clicks and conversions event streams.
Who should apply? Teams of 3-5 people, with hands-on knowledge of machine learning algorithms, and ability to quickly set up a working processing pipeline (using MapReduce, Apache Spark, or any other framework that can process terabytes of data stored in S3 within a few hours.
The hardware: The dataset will be placed on AWS S3. You will be provided with an AWS account where you’d be able to code and deploy your solution. Previous knowledge of the AWS ecosystem is recommended. Our mentors will be able to assist where needed.
Who wins? The winner will be chosen based on a score with two factors: quality of solution (distance from actual results), and performance – the faster the better.