Artykuł w czasopiśmie
Brak miniatury
Licencja
ClosedAccessDostęp zamknięty
 

Predicting winrate of hearthstone decks using their archetypes

Uproszczony widok
dc.abstract.enThis paper describes our solution for the AAIA'18 Data Mining Challenge: Predicting Win-rates of Hearthstone Decks. Train and test decks were clustered by DBSCAN algorithm with precomputed distance matrix dependent on the number of common cards. We observed that each cluster can be represented by an archetype deck - one of popular decks used by human players. For each deck we created features describing cards quality and types. Additionally we used differences of these features with respect to archetype decks. Finally we used XGBoost to build a model predicting outcome of a game played between two decks.
dc.affiliationUniwersytet Warszawski
dc.conference.countryPolska
dc.conference.datefinish2018-09-12
dc.conference.datestart2018-09-09
dc.conference.placePoznań
dc.conference.seriesCONFERENCE ON COMPUTER SCIENCE AND INTELLIGENCE SYSTEMS
dc.conference.seriesCONFERENCE ON COMPUTER SCIENCE AND INTELLIGENCE SYSTEMS
dc.conference.seriesshortcutFedCSIS
dc.conference.shortcutFedCSIS 2018
dc.conference.weblinkhttps://fedcsis.org/2018/
dc.contributor.authorSztyber, Anna
dc.contributor.authorBetley, Jan
dc.contributor.authorWitkowski, Adam
dc.date.accessioned2024-01-25T17:32:37Z
dc.date.available2024-01-25T17:32:37Z
dc.date.issued2018
dc.description.financeNie dotyczy
dc.identifier.doi10.15439/2018F362
dc.identifier.issn2300-5963
dc.identifier.urihttps://repozytorium.uw.edu.pl//handle/item/116911
dc.identifier.weblinkhttps://annals-csis.org/proceedings/2018/drp/362.html
dc.languageeng
dc.pbn.affiliationcomputer and information sciences
dc.relation.ispartofAnnals of Computer Science and Information Systems
dc.relation.pages193-196
dc.rightsClosedAccess
dc.sciencecloudnosend
dc.titlePredicting winrate of hearthstone decks using their archetypes
dc.typeJournalArticle
dspace.entity.typePublication