Skip to content

yang1fan2/Dota2-Prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

45 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time Dota2 Match Result Prediction

In this project, we try to predict the winning team of a Dota2 match. We consider prior (pre-match) features from individual players' match history, as well as real-time (during-match) features at each minute as the match progresses. We use logistic regression, the proposed Attribute Sequence Model, and their combinations as the prediction models. In a dataset of 78362 matches where 20631 matches contain replay data, our experiments show that adding more aspects of prior features improves accuracy from 58.69% to 71.49%, and introducing real-time features achieves up to 93.73% accuracy when predicting at the 40th minute.

Training

pip install keras==1.0.0
cd match_data; unzip new_match.zip
cd ../models; python2 lr.py
# Please use Theano as the backend

Dota dataset stored as MongoDB dump (2.35 GB, 1M matches, 20K players and 111 heros). Crawled via the APIs.

Availabe in Google Drive. There are four collections in mongoDB (db name is 701)

Reference

Please find more information from this paper

@article{yang2016real,
  title={Real-time esports match result prediction},
  author={Yang, Yifan and Qin, Tian and Lei, Yu-Heng},
  journal={arXiv preprint arXiv:1701.03162},
  year={2016}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages