This thesis presents a comprehensive analysis of chess openings through the lens of data science. Utilizing the python-chess library, this study analyzes millions of chess games and thousands of opening sequences to define the term of ‘sharpness’ in chess openings and to evaluate if it relates to popularity in different levels of play. The methods used in the study involve data mining, extraction, and transformation in addition to statistical modeling, leveraging Python for all of these methods. Keyfindings of the research indicate that sharpness can be quantified and sorted through chess engine evaluations and applied to opening sequences. Another key finding is that the preferences of opening choice vary significantly between low-level and high-level players. The results point out certain opening sequences that should beintroduced to players’ opening repertoires based on the sharpness factor. The significance of this research is its contribution to both the field of data science and the chess community. For data scientists and statisticians, it showcases the application of analytical techniques to define a new take on the fuzzy concept of sharpness in such a complex game as chess. For chess players and enthusiasts, it offers a new perspective on opening strategies, potentially enhancing their opening theory knowledge.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:du-48522 |
| Date | January 2024 |
| Creators | Salmi, Samuli |
| Publisher | Högskolan Dalarna, Mikrodataanalys |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0017 seconds