Matching Items (5)

135980-Thumbnail Image.png

Developing a Model to Predict Match Outcomes in League of Legends

Description

League of Legends is a popular multiplayer online battle arena (MOBA) developed by Riot Games. Each team consists of 5 players who each control a single character (champion) which they

League of Legends is a popular multiplayer online battle arena (MOBA) developed by Riot Games. Each team consists of 5 players who each control a single character (champion) which they select at the beginning of each game. In order to win the match, a team has to destroy the Nexus (the central structure) in the opponent's base. League of Legends has grown rapidly since its release in 2009 and has over 70 million registered players. Several community websites have been created that track the performance of players and show detailed statistics for just about every aspect of the game. This project focuses on exploring the applicability of predictive analytics within League of Legends, by predicting the outcome of any given ranked match at the start of the game. It resulted in a model with accuracy of 58% using decision trees. An additional contribution of the project is a solution to a data collection anomaly that has biased previous studies.

Contributors

Agent

Created

Date Created
  • 2015-12

133684-Thumbnail Image.png

Predicting the Outcome of UFC Fights Using Machine Learning Models

Description

Abstract: The Ultimate Fighting Championship or UFC as it is commonly known, was founded in 1993 and has quickly built itself into the world's foremost authority on all things MMA

Abstract: The Ultimate Fighting Championship or UFC as it is commonly known, was founded in 1993 and has quickly built itself into the world's foremost authority on all things MMA (mixed martial arts) related. With pay-per-view and cable television deals in hand, the UFC has become a huge competitor in the sports market, rivaling the popularity of boxing for almost a decade. As with most other sports, the UFC has seen an influx of various analytics and data science over the past five to seven years. We see this revolution in football with the broadcast first down markers, basketball with tracking player movement, and baseball with locating pitches for strikes and balls, and now the UFC has partnered with statistics company Fightmetric, to provide in-depth statistical analysis of its fights. ESPN has their win probability metrics, and statistical predictive modeling has begun to spread throughout sports. All these stats were made to showcase the information about a fighter that one wouldn't typically know, giving insight into how the fight might go. But, can these fights be predicted? Based off of the research of prior individuals and combining the thought processes of relevant research into other sports leagues, I sought to use the arsenal of statistical analyses done by Fightmetric, along with the official UFC fighter database to answer the question of whether UFC fights could be predicted. Specifically, by using only data that would be known about a fighter prior to stepping into the cage, could I predict with any degree of certainty who was going to win the fight?

Contributors

Agent

Created

Date Created
  • 2018-05

135558-Thumbnail Image.png

Value of Twitter: Using Text Mining Methods to Gain Insight into the 2016 Presidential Race

Description

This project analyzes the tweets from the 2016 US Presidential Candidates' personal Twitter accounts. The goal is to define distinct patterns and differences between candidates and parties use of social

This project analyzes the tweets from the 2016 US Presidential Candidates' personal Twitter accounts. The goal is to define distinct patterns and differences between candidates and parties use of social media as a platform. The data spans the period of September 2015 to March 2016, which was during the primary races for the Republicans and Democrats. The overall purpose of this project is to contribute to finding new ways of driving value from social media, in particular Twitter.

Contributors

Created

Date Created
  • 2016-05

133499-Thumbnail Image.png

Investigating the Relationship between Neighborhood Socioeconomic Status and Proximity to Public Services

Description

With growing levels of income inequality in the United States, it remains as important as ever to ensure indispensable public services are readily available to all members of society. This

With growing levels of income inequality in the United States, it remains as important as ever to ensure indispensable public services are readily available to all members of society. This paper investigates four forms of public services (schools, libraries, fire stations, and police stations), first by researching the background of these services and their relation to poverty, and then by conducting geospatial and regression analysis. The author uses Esri's ArcGIS Pro software to quantify the proximity to public services from urban American neighborhoods (census tracts in the cities of Phoenix and Chicago). Afterwards, the measures indicating proximity are compared to the socioeconomic statuses of neighborhoods using regression analysis. The results indicate that pure proximity to these four services is not necessarily correlated to socioeconomic status. While the paper does uncover some correlations, such as a relationship between school quality and socioeconomic status, the majority of the findings negate the author's hypothesis and show that, in Phoenix and Chicago, there is not much discrepancy between neighborhoods and the extent to which they are able to access vital government-funded services.

Contributors

Agent

Created

Date Created
  • 2018-05

135606-Thumbnail Image.png

Data Analysis of Jungle Pattern in League of Legends with Implications for Players and Game Developers

Description

League of Legends is a Multiplayer Online Battle Arena (MOBA) game. MOBA games are generally formatted where two teams of five, each player controlling a character (champion), will try to

League of Legends is a Multiplayer Online Battle Arena (MOBA) game. MOBA games are generally formatted where two teams of five, each player controlling a character (champion), will try to take each other's base as quickly as possible. Currently, with about 70 million, League of Legends is number one in the digital entertainment industry with $1.63 billion dollars of revenue in year 2015. This research analysis scopes in on the niche of the "Jungler" role between different tiers of player in League of Legends. I uncovered differences in player strategy that may explain the achievement of high rank using data aggregation through Riot Games' API, data slicing with time-sensitive data, random sampling, clustering by tiers, graphical techniques to display the cluster, distribution analysis and finally, a comprehensive factor analysis on the data's implications.

Contributors

Agent

Created

Date Created
  • 2016-05