The results of the
first round of the
Data Clustering Contest are in.
In our evaluation, the
quality of sorting in tasks 1-4 had the greatest influence. The more subjective task 5 (sorting threads by relative importance) carried a lower weight. Overall
speed of the algorithms influenced the final score.
More detailed statistics for each of the submissions are available in our latest comments on
contest.com. You can also view articles for two additional days in the interface – Jan 31 and Feb 14.
In addition to the main prizes, we are awarding bonus prizes to those solutions that delivered
significantly better results than the rest of the submissions in each of the tasks. If a submission required adjustments or fixes to make it work, it was penalized accordingly.
1st PLACE🥇 Swift Skunk –
€17,000 + €4,900 bonusBonus prizes for:
- Language detection
- News, English
- Categories, Russian
- Threads, English
- Threads, RussianBug fixing penalties (-€100):
- Invalid output format2nd PLACE🥈 Bossy Gnu –
€13,000 + €2,800 bonusBonus prizes for:
- News, English
- Categories, English
- Categories, RussianBug fixing penalties (-€200):
- Invalid output format x2 (extra comma; unescaped quote)🥈 Hip Hyena –
€13,000 + €1,000 bonusBonus prize for:
- Top news, Russian3rd PLACE🥉 Mindful Squirrel –
€6,500 + €2,800 bonusBonus prizes for:
- News, English
- News, Russian
- Categories, RussianBug fixing penalties (-€200):
- Build manually due to an error🥉 Kooky Dragon –
€6,500 + €2,000 bonusBonus prizes for:
- News, English
- Categories, English🥉 Gifted Lemur –
€6,500 + €800 bonusBonus prizes for:
- Categories, EnglishBug fixing penalties (-€200):
- Algorithm required additional articles to work4th place🏅
Ace Cock –
€4,500🏅
Sharp Sloth –
€4,300Bug fixing penalties (-€200):
- Invalid output format x2 (unencoded \n; unencoded \)Several participants achieved some of the best results in tasks
1-3, but didn't get a high enough score in the later stages to compete for the main prizes. They are receiving bonus awards for those tasks in which their solutions were significantly better than the rest.
Bonus Awards🎖 Shiny Quokka –
€1,000-
Categories,
English🎖 Stone Gnat –
€1,000-
News,
Russian🎖 Large Crab –
€900- Language detection (€1,000)
- Invalid output format (-€100)🎖Grim Wombat –
€900- Top news, English (€1,000)
- Invalid output format (-€100)
🎖 Little Swan – €
800- Language detection (€1,000)
- Build manually due to a missing package (-€200)
🎖 Huge Flamingo –
€700- Categories, Russian (€1,000)
- Algorithm required additional articles to work (-€200)
- Algorithm had to be re-run from a different folder (-€100)
The second round of the Data Clustering contest will be open for everyone to participate. We look forward to announcing new contests and more results in the coming weeks.
Stay tuned!