mberk / rss-euro-2020-prediction-competition Goto Github PK
View Code? Open in Web Editor NEWThe official GitHub repository of the RSS Euro 2020 Prediction Competition
The official GitHub repository of the RSS Euro 2020 Prediction Competition
I'm starting a project to predict football scores based on previous odds and previous scores and I was wondering if you would like to stay in touch with me
Hello, I was wondering, what happens to my score if my submission's probability prediction does not add to 1? For example, if I predict Team 1 to beat Team 2 at 90% probability and the opposite at 20% probability (even though it should be 10%).
Hi,
I have emailed a similar comment several days ago so apologies if this is duplication but I wanted to ensure my question was seen before the knockouts resumed. Thanks for running the tournament, I'm enjoying keeping track of the table and my anonymous competitors!
On the group stages, probabilities are normalised by L43-45 of'score_submissions.py
to ensure all possible outcomes sum to a probability of 1.
For the knockout rounds, this is not done again. It seems that the competition has defined draws as impossible events in knockout round matches, suggesting P(team1)+P(team2) =1. In practice, a non-zero likelihood is given to the impossible draw . Therefore, should knockout round team1 and team2 probabilities similarly be normalised akin to how group matches are, but ignoring the probability for draws please?
i.e
df_ko["p_team1_win"] = df_ko["p_team1_win"]/df_ko[["p_team1_win", "p_team2_win"]].sum(axis=1)
Thanks for any clarification you can give here!
Again in the interests of disclosure I am asking this because I have non zero probabilities for draws in knockout round games, a subtlety to the rules that I did not appreciate when submitting my entry.
Best wishes
Hello thanks for hosting this competition, sounds very interesting, I would like to clarify rule #2 :
"Entrants are free to use any data they wish, provided it is publicly available".
Does data scraped from websites count as "publicly available"?
I also assume there is a "one submission per person" rule...
Hello, when it says "two entries with the best log-score (see Scoring below) will win a prize (see Prizes below) along with a third entry chosen by the judging panel based on the methodology used".
Are we allowed to include a written report in our submission file to improve our chances of getting the prize for "third entry chosen by the judging panel based on the methodology used"?
Hi there, I was wondering if you still had ambitions to get the live leaderboard up and running? It would be really interesting to see how we were doing compared to the other teams, even if the updates were only infrequent.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.