What is a Datathon?

The Datathon is a weekend-long online competition where you are challenged to work on a real-world business case from the areas of computer vision, NLP and AI.

You and your team have 48 hours to come up with a solution to a real business challenge based on the provided datasets. The jury and the society will award the most precise, but also creative solutions.

The Datathon is entirely held online and opened to the global community via our platform. Anyone who wants to join us in Sofia is welcome.

What is Datathon?

Why participate?

Face real-world challenges

Solve practical business challenges in the areas of AI, NLP, computer vision, image processing and more

Have fun
We urge you to have fun at this gathering of like-minded people: connect, explore and grow as experts together
Leading experts mentoring

Receive mentoring from some of the best experts in AI, NLP, computer vision, image processing and other

Network
You get to work in a team of experts in diverse fields and also receive advice from our company and invited mentors
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 the companies that provided the cases
Virtual machines Microsoft, Amazon or IBM cloud
Supreme Mentorship from domain world experts
A platform for collaboration within Data Science Society

How it works:

Reserve your spot via Eventbrite
Register on the website and fill in your profile beginning of February
Review the Datathon cases
Book your time slots with mentors
Use the platform to proactively form your team
Grand opening start working with your team
Work with mentors
Upload your results on the DSS platform for review
Awards and feedback

The cases

These are the real cases coming from the companies. We want to thank them for the effort to anonymize the data and be part of this initiative.

Be bold and pick one or comment in our social channels!

Receipt Bank

CV case

The task will be to develop an algorithm that detects how many documents are contained in a PDF file.

More info

Telenor

SNA case

The task is to investigate social structures through the use of networks and graph theory.

More info

Identrics

NLP case

The task is to extract words, representative for entity’s activities and properties in а specified context of interest in news articles.

More info

ZenCodeo

NLP case

The task will be to find the model that assigns one and the same company ID to the two or more similar records, assuming it is the same Entity.

More info

VMware

NLP case

Your task will be cluster similar KB articles together so that they form clusters where the same problem is discussed.

More info

Kaufland

CV case

The task is to build up an image recognition that reliably recognizes which type of vegetables the customer has selected.

More info

Telelink

DNA case

The task is to obtain the complete set of genome traces found in a single food sample and ALL organisms that should not be found in the food sample.

More info

Ontotext

NLP case

The task is to train ML on text that is annotated with concepts and relations that WE KNOW ABOUT from Open Data.

More info

SAP

AI case

The task will be to identify the volume uplift drivers, measure the promotional effectiveness and measure the cannibalization effect from main competitors.

More info

The Experts

Our partners provided Industry Experts for the cases and Platform Experts to help you with setting up your work space.

Schedule

Pre-event week

  1. Registration on the DDS website - mandatory for all participants
  2. Fill in your profiles
  3. Get to know the cases and the DSS platform
  4. Chat with the Industry Experts
  5. End registration for matchmaking process
  6. Chat with Mentors
  7. Get to know other participants & Pre-event team forming

Day 1 - 09.Feb.18

  1. Registration
  2. Q&A & Networking
  3. #Datathon2018 Launch
  4. Welcome by the host - T.Sedlarski, Dean of FEBA
  5. Introduction to the #Datathon2018
  6. /Mentors, Cases, Technical Partners, DSS Platform, Datathon Workflow, Q & A/
  7. End of the Official Openning of #Datathon2018
  8. ***
  9. Only for participants @ Faculty of Economics and Business Administration & Online
  10. Fun session 1: Ice Breaking
  11. Matchmaking
  12. Fun session 2: Networking, Team forming & Beer
  13. Deadline for Team Registration

Day 2 - 10.Feb.18

  1. Fun session 3: Surprise
  2. Breakfast
  3. Lunch
  4. Fun session 4: Surprise
  5. Dinner

Day 3 - 11.Feb.18

  1. Breakfast
  2. Semi-Finals Groups Announcement
  3. Fun Session 5: Surprise
  4. Deadline for Publishing Results
  5. Semi-Finals - Jury
  6.       Finals Opening
  7. ***
  8. Finalists Announcements
  9. Presentations by the finalists via Hangout
  10. Finals - Jury
  11. Fun Session 6: Surprise
  12. Awards
  13. Fun Session 7: Party

Q&A

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 Datathon.

However, we advise you to register on the Datathon as soon as possible in order to review the cases and start communicating with other participants in order to form your team.

Your team’s solutions will be evaluated according to several criteria - statistical indicators, resourcefulness of the solution and creativity of visualization.

You can use the output data and other information provided to you in regard to solving the chosen case only during the duration of the event. You must not use those for personal or 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.

After purchasing a ticket, you will receive an email with instructions on where and how to register on the Datathon website and start forming your team.

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.

If you already have obtained a ticket via Eventbrite, you will receive an email with instructions on how to register on the Datathon platform. Please register and start browsing the cases 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 chat room(s) for the case(s) that you find interesting. This is a good way to find other experts that would like to work on the same case.

If you already have obtained a ticket via Eventbrite, you will receive an email with instructions on how to register on the Datathon platform. Please register and start browsing the cases and other registered participants. You will be able to form a team with ease once you have chosen a case to work on.

We suggest the following workflow to choose a case:

  1. Review all the provided cases
  2. Look for a case that will challenge and excite you
  3. Form or join a team that you will have fun with

Eventbrite registrations will end one week before the event on February 2nd 2018.

Registration on the Datathon website will not be closed, so you can register to participate throughout the even or join later to review what other participants have achieved.

Powered by:

Our Partners:

Organizers:

Data Science Society is a community of people dedicated to promoting better collaboration between science, education and business, to accelerate ethical and open innovation in the Data Science domain.

General Terms of Participation

With your registration, you accept the following conditions: