The Academia Datathon is a weekend-long online competition where more than 100 students from several universities across 6 countries are challenged to work on one real-world business case.
Their mission is to build in 48 hours not only the best machine learning algorithms but also to build up their knowledge and expertise helped by mentors, experts and other like-minded students in the field coming from all over the world.
The most creative and precise solutions of the provided dataset for the challenge will be awarded by a world known jury.
The Academia Datathon is entirely held online and opened to the global community via our platform.
Call For Professors
Every University can participate
if there is at least one professor willing to work with his students for a weekend and secure a venue.
The case is financial time-series prediction with cryptocurrencies and it integrates knowledge from various sources - Crypto Currencies, Quantitative Finance, and Machine learning.
The Data
The data consists of time-series of various cryptocurrencies with open, high, low, close prices and volumes from different crypto exchanges, but it could also be enriched during the Datathon by the teams.
Two levels of difficulty
The first level is to make a prediction model of the major cryptocurrencies’ prices with all necessary studies for that purpose. The second level is making an autonomous A.I. decision-maker for trading/investing.
The Goal
The goal is to build a successful investing/trading model on the cryptocurrency markets.
Good luck!
The Academia:
The Mentors
This is the top University Mentors team with huge experience in #Econometrics, #Statistics and #ComputerScience.
Solve a practical cryptocurrency challenge, using Machine Learning, AI algorithms and more
Have fun
We encourage all students to have fun, form a team of other like-minded students, compete together, connect, and master Data Science learning from each other.
Leading Experts Mentorship
Get mentored by some of the best experts in Cryptocurrency and Machine Learning
Network
Work with fellow students from all around the world while receiving advice from DSS experts and other mentors and professors.
Be a part of the community
Be a part of a strong and focused on data science only community that strives to grow our expertise together
Safe learning environment
Grow your knowledge and experiment in the safe and supportive environment of Data Science Society
Access to:
Real data from sources providing Cryptocurrency transactions
Various cryptocurrencies with prices and volumes from different cryptocurrency exchange
Data Science Challenges with multiple levels of difficulty – Prediction models and AI algorithms
A platform for collaboration within Data Science Society and Supreme Mentorship from domain world experts
How it works:
Reserve your spot via the link sent by your professor
Register on the website and fill in your profile beginning of April
Review the Datathon case
Form your team by using the platform proactively
Opening, start working with your team
Work with mentors
Upload your results on the DSS.Platform
Awards and feedback
The Society Mentors
Data Science Society provided Domain Experts for the case to help you with setting up your workspace and also with the questions you might have during the development of your Data masterpiece solutions.
I don’t have a team, yet. Can I take part in the datathon?
Yes. It is not mandatory to have a team formed in order to participate. You will have a chance to form a team virtually up until the start of the Academia Datathon and it doesn't matter if it will be only with students of your University or if you prefer being part of an international team.
However, we advise you to register on the Academia Datathon as soon as possible in order to review the case and to start communicating with other participants in the DataChat in order to form your team.
How will my solution be evaluated?
Your team's solutions will be evaluated according to several criteria - statistical indicators, the resourcefulness of the solution (article) and creativity of visualization.
We are working on a solution for automatic scoring of results as a supplementary tool for the judgement process.
Can I use the data & algorithms developed afterwards?
You can use the output data and other information provided to you in regard to solving the chosen case during the duration of the event. You must not use those for commercial purposes outside the event format and activities. With the registration for the Datathon, you agree to also provide your work (analysis, methodology, source code, etc) to the organizers for them to publish on the event page.
How do I join the Datathon virtually?
You need to register online and use Data.Platform. Follow Data.Chat discussions, form a team and monitor our online streaming.
How do I present my solution if I participate virtually?
You will submit your work as an article when the 48 hours of the challenge are over. After an evaluation, a list of finalists will be selected. The selected teams will present their cases via Hangouts or Data.Chat.
How do I form a team if I am participating virtually?
Please register at Data.Platform and start browsing the case and other registered participants. You will be able to form a team with ease once you have chosen a case to work on.
We also advise you to take a look at the profiles of other participants and start using the Data.Chat. This is a good way to find other experts that would like to work with you.
How do I choose a case to work on?
If you already have obtained a ticket with your university code in the registration, you will receive an email with instructions. You can then start think about the case and to browser other registered participants if you still don`t have a team to participate with.
When does the registration end?
The registration will end one week before the event on April 20th 2018.
Even if you don't participate you can later check the Datathon solutions and review what other participants have achieved.
General Terms of Participation
With your registration, you accept the following conditions:
