A chess rating system that accounts for draws and the advantage of playing as white
Main Article Content
Abstract
We introduce a chess rating system based on a preference model that includes an explicit parameter for draws, modified to account for the advantage of playing white. Heuristics derived from the conditional maxima of the hierarchical Bayesian model yield straightforward updating formulas. To illustrate the system’s potential for describing past performance and predicting game results, we present the updating process using a small synthetic example and data from a recent tournament featuring elite chess players. The results are discussed and compared with other systems. The proposed system is competitive both in describing past performance and in predicting outcomes. It is flexible and has the potential to be used either as a chess rating system or to evaluate other sports where draws are possible.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
1. Chess.com. Chess Terms https://www.chess.com/terms/elo-rating-chess.
2. Davidson, R. R. On extending the Bradley-Terry model to accommodate ties in paired comparison experiments. Journal of the American Statistical Association 65, 317–328 (1970).
3. Dempster, A. P., Laird, N. M. & Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B 39, 1–22 (1977).
4. Elo, A. E. The rating of chessplayers, past and present (Arco Pub., 1978).
5. Glickman, M. E. Example of the Glicko-2 system. Boston University, 1–6 (2012).
6. Glickman, M. E. The glicko system. Boston University 16, 16–17 (1995).
7. Glickman, M. E.&Doan, T. TheUSCF rating system.URL http://www. glicko. net/ratings/rating. system. pdf (2010).
8. Glickman, M. E. & Jones, A. C. Rating the chess rating system. CHANCE 12, 21–28 (1999).
9. Joe, H. Extended use of paired comparison models, with application to chess rankings. Journal of the Royal Statistical Society Series C: Applied Statistics 39, 85–93 (1990).
10. Lew, A. K., Matheos, G., Tan Z.-X., T., Ghavamizadeh, M., Gothoskar, N., Russell, S. & Mansinghka, V. K. Smcp3: Sequential monte carlo with probabilistic program proposals in International Conference on Artificial Intelligence and Statistics (2023), 7061–7088.
11. Marques, R. A. G. On Monte Carlo contributions for real-time probabilistic inference eng. Oslo, 2018.
12. Meng, X.-L. & Rubin, D. B. Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika 80, 267–278 (1993).
13. Nolan, E. & Scognamillo, V. Online Chess Social Networks (2021).
14. Pires, D. M. & Bueno Filho, J. S. S. CAN ELO RATINGS BE IMPROVED? A CASE STUDY WITH ELITE CHESS PLAYERS. Brazilian Journal of Biometrics 38, 483–505 (2020).
15. Sismanis, Y. How i won the" chess ratings-elo vs the rest of the world" competition. arXiv preprint arXiv:1012.4571 (2010).
16. Sonas, J. Chessmetrics http://www.chessmetrics.com/cm/. 2005.
17. Stephenson, A. & Sonas, J. Playerratings: Dynamic updating methods for player ratings estimation [Computer software manual] 2016.
18. Tata Steel Chess Tournament https://tatasteelchess.com. May 2023.