Project Overview

Board-game Consultants:

Shimin Bi; Chen Shi; Yanying Qiu; Melissa Zhao

Background and Motivation

We all love "Sushi Go!", but what is it about "Sushi Go!" that makes it so addictive? There are many different components of a board game that give it a lot of variations. Different board games can have various maximum or minimum number of players, varying length of play time, different themes, mechanisms, designers or even different difficulty! We are curious to find out which of these attributes actually make a board game a good one, measured by player ratings. With data collected from boardgamegeek.com, we have player ratings on thousands of board games and their features. We are interested to do some exploratory analysis on the features and potentially build models to predict which board games are more likely to be loved by players.

Objectives

Investigate the possible traits of high-rating board games using ggplot2 package in R.
Build models to predict the success of a new board game and find important features of the successful games (defined by high average player rating).
Recommend board games to players based on certain specified criteria or other games that they love.

Study Design

We analyzed a comprehensive dataset with 4999 board games. Each game was a row with column information on number of players, time spent, rating, age of players, mechanic, category, designer, and weight. The following steps were planned and performed in sequential order:

Data cleaning with data wrangling methods to create helpful categorical data (ie. single player, multi-player, party games; short, medium, long play times; easy, moderate, difficult games), missing data treatment (manually reread games with 0 zeros for certain variables, such as play time, year) and outlier removal (ie. recommended player age of 42).
Exploratory data analysis on all the covariates, including:
- Summary figures of interesting characteristics and associations found within the dataset
- Analysis on the time-related covariates
- Specific analysis of game mechanics and game categories covariates
Machine learning methods to build a predictor model for game average ratings, including:
- linear regression
- kth nearest neighborhood
- random forest
- support vector machine
Board game recommender using Euclidean distance between board game covariates.

Data Source

Our data comes from an open data set on Kaggle. The data set contains information about 4999 boardgames in a time range from ancient times to 2018. It includes features such as average time needed to play each game, minimum and maximum players, year of publication, designer, difficulty level, mechanics, categories, etc.

Link: https://www.kaggle.com/mrpantherson/board-game-data

References

Sicart, Miguel (1 December 2008). "Defining Game Mechanics". Game Studies. 8 (2). ISSN 1604-7982. Retrieved 22 June 2016.
Adams, Ernest; Rollings, Andrew (2003). Andrew Rollings and Ernest Adams on game design. New Riders Publishing. ISBN 1-59273-001-9.
Adams, Ernest; Dormans, Joris (2012). Game Mechanics: Advanced Game Design. California: New Riders Games, an imprint of Peachpit. ISBN 978-0-321-82027-3.
Board Game Design Lab: http://www.boardgamedesignlab.com/design-theory/
Boardgamegeek.com, website from which dataset was extracted: https://boardgamegeek.com/browse/boardgame

Google Sites

Report abuse