Abstract
We propose Exceptional Gestalt Mining (EGM), a variant of Exceptional Model Mining that seeks subgroups of the dataset where a coalition becomes more than the sum of its parts. Suppose a dataset of games in which several roles exist within a team; the team can combine forces from any subset of roles, to achieve a common goal. EGM seeks subgroups for which games played employing a large role set have a higher win rate than games played employing any strict subset of that role set. We illustrate the knowledge EGM can uncover by deploying it on a dataset detailing Magic: The Gathering games: we find combinations of cards that jointly work better in multicolor decks than in decks employing fewer colors. We argue that EGM can be deployed on datasets from sports where several roles exist that directly interact in play, such as ice hockey.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Most of our descriptions of the game are not completely accurate. With over 20 000 distinct cards there is an exception to almost any generalization. In this case: some lands can produce mana of multiple colors, or produce no mana at all. Our descriptions only serve to illustrate the context of the dataset.
- 2.
Cards can react to in-game events with new effects of their own and the game rules define that if an unbreakable loop occurs, then the game is a draw; simulating a Turing machine with the available cards is nontrivial, but was finally achieved in 2019 after multiple steps of partial progress.
- 3.
Depending on what a specific sports league allows, this may include the current main squad, youth players, minor league affiliate team players, loan players, and players acquired in mid-season transfers.
- 4.
In fact, one standard hockey player performance metric, called +/–, acknowledges that good defenders enable a strong offense and good offensive lines contribute to a strong defense. The metric records the number of goals the team scores while you are on the ice, minus the number of goals the team concedes while you are on the ice. Hence, top-scoring centers or wingers who neglect their defensive duties can be found out by comparing their performance in terms of goals and assists with their performance in terms of +/–.
- 5.
There may be multiple granularities on which roles make sense. For instance, in a hockey team, one can specify \(\mathcal {R}=\{\text {defender, goalkeeper, forward}\}\) or \(\mathcal {R}=\{\text {center, defender, goalkeeper, left winger, right winger}\}\). In Exceptional Gestalt Mining, we need to pick one set of roles, and stick with it.
- 6.
- 7.
Compare the discussion of the Raise the Draugr/Glittering Frost in Sect. 5.1.
References
Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of VLDB, pp. 487–499 (1994)
Bay, S.D., Pazzani, M.J.: Detecting group differences: mining contrast sets. Data Min. Knowl. Discov. 5(3), 213–246 (2001)
Bosch, R.A.: Optimal card-collecting strategies for magic: the gathering. College Math. J. 31(1), 15–21 (2000)
Chatterjee, K., Ibsen-Jensen, R.: The complexity of deciding legality of a single step of magic: the gathering. In: Proceedings of European Conference on AI (2016)
Cowling, P.I., Ward, C.D., Powley, E.J.: Ensemble determinization in Monte Carlo tree search for the imperfect information card game magic: the gathering. IEEE Trans. Comp. Int. AI Games 4(4), 241–257 (2012)
Churchill, A., Biderman, S., Herrick, A.: Magic: The Gathering is Turing Complete (2019). arXiv preprint: arXiv:1904.09828 [cs.AI]
Conroy, R.: Do the Bots Send Signals? 01 July 2019. https://www.17lands.com/blog/bot_signals. Accessed 16 June 2021
Conroy, R.: Impact of the London Mulligan, 23 October 2019. https://www.17lands.com/blog/london_mulligan. Accessed 16 June 2021
Conroy, R.: Simulated Draft Strategies, 28 July 2020. https://www.17lands.com/blog/simulating_draft_strategies. Accessed 16 June 2021
Dong, G., Li, J.: Efficient mining of emerging patterns: discovering trends and differences. In: Proceedings of KDD, pp. 43–52 (1999)
Du, X., Pei, Y., Duivesteijn, W., Pechenizkiy, M.: Exceptional spatio-temporal behavior mining through Bayesian non-parametric modeling. Data Mining Knowl. Disc. 34(5), 1267–1290 (2020). https://doi.org/10.1007/s10618-020-00674-z
Duivesteijn, W., Feelders, A.J., Knobbe, A.: Exceptional model mining - supervised descriptive local pattern mining with complex target concepts. Data Mining Knowl. Discov. 30(1), 47–98 (2016)
Garfield, R.C.: Trading card game method of play. United States Patent US5662332A, United States Patent and Trademark Office, 02 September 1997
Giacometti, A., Soulet, A.: Dense neighborhood pattern sampling in numerical data. In: Proceedings of SDM, pp. 756–764 (2018)
Herrera, F., Carmona, C.J., González, P., del Jesus, M.: An overview on subgroup discovery: foundations and applications. Knowl. Inf. Syst. 29(3), 495–525 (2011)
Klösgen, W.: Explora: a multipattern and multistrategy discovery assistant. Advances in Knowledge Discovery and Data Mining, pp. 249–271 (1996)
Konijn, R.M., Duivesteijn, W., Kowalczyk, W., Knobbe, A.J.: Discovering local subgroups, with an application to fraud detection. Proc. PAKDD 1, 1–12 (2013)
Kralj Novak, P., Lavrac, N., Webb, G.I.: Supervised descriptive rule discovery: a unifying survey of contrast set, emerging pattern and subgroup mining. J. Mach. Learn. Res. 10, 377–403 (2009)
17 Lands: KHM Traditional Draft Game Data, 04 April 2021. https://17lands-public.s3.amazonaws.com/analysis_data/game-data.KHM.TradDraft.tar.gz. Accessed 17 June 2021
17 Lands: Public Datasets. https://www.17lands.com/public_datasets. Accessed 17 June 2021
Leman, D., Feelders, A., Knobbe, A.: Exceptional Model Mining. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5212, pp. 1–16. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87481-2_1
Lucking-Reiley, D.: Using field experiments to test equivalence between auction formats: magic on the internet. Am. Econ. Rev. 89(5), 1063–1080 (1999)
Martin, B.A.S.: Using the imagination: consumer evoking and thematizing of the fantastic imaginary. J. Consum. Res. 31(June), 136–149 (2004)
Sierkovitz: 5000 Words for Snow, 18 February 2021. https://www.17lands.com/blog/khm_snow_decks. Accessed 16 June 2021
Sierkovitz: Servant, not Master, 27 April 2021. Available online at https://www.17lands.com/blog/using_wr_data. Accessed 16 June 2021
Wrobel, S.: An Algorithm for multi-relational discovery of subgroups. In: Proceedings of PKDD, pp. 78–87 (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Duivesteijn, W., van Dijk, T.C. (2022). Exceptional Gestalt Mining: Combining Magic Cards to Make Complex Coalitions Thrive. In: Brefeld, U., Davis, J., Van Haaren, J., Zimmermann, A. (eds) Machine Learning and Data Mining for Sports Analytics. MLSA 2021. Communications in Computer and Information Science, vol 1571. Springer, Cham. https://doi.org/10.1007/978-3-031-02044-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-02044-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02043-8
Online ISBN: 978-3-031-02044-5
eBook Packages: Computer ScienceComputer Science (R0)