Filtering by
- All Subjects: Data Analytics
- Creators: Department of Information Systems
- Resource Type: Text
- Status: Published
In recent years, advanced metrics have dominated the game of Major League Baseball. One such metric, the Pythagorean Win-Loss Formula, is commonly used by fans, reporters, analysts and teams alike to use a team’s runs scored and runs allowed to estimate their expected winning percentage. However, this method is not perfect, and shows notable room for improvement. One such area that could be improved is its ability to be affected drastically by a single blowout game, a game in which one team significantly outscores their opponent.<br/>We hypothesize that meaningless runs scored in blowouts are harming the predictive power of Pythagorean Win-Loss and similar win expectancy statistics such as the Linear Formula for Baseball and BaseRuns. We developed a win probability-based cutoff approach that tallied the score of each game once a certain win probability threshold was passed, effectively removing those meaningless runs from a team’s season-long runs scored and runs allowed totals. These truncated totals were then inserted into the Pythagorean Win-Loss and Linear Formulas and tested against the base models.<br/>The preliminary results show that, while certain runs are more meaningful than others depending on the situation in which they are scored, the base models more accurately predicted future record than our truncated versions. For now, there is not enough evidence to either confirm or reject our hypothesis. In this paper, we suggest several potential improvement strategies for the results.<br/>At the end, we address how these results speak to the importance of responsibility and restraint when using advanced statistics within reporting.
Home advantage affects the game in almost all team sports across the world. Due to<br/>COVID and all of the precautions being taken to keep games played, more extensive research is able to be conducted about what factors truly go into creating a home advantage. Some common factors of home advantage include the crowd, facility familiarity, and travel. In the English Premier League, there are no fans allowed at any of the games; furthermore, in the NBA, a bubble was created at one neutral venue with no fans in attendance. Even with the NBA being at a neutral site, there was still a “home team” at every game. The sports betting industry struggled due to failing to shift betting lines in accordance with this decreased home advantage. With these leagues removing some of the factors that are frequently associated with home advantage, analysts are able to better see what the results would be of removing these variables. The purpose of this research is to determine if these adjustments made due to COVID had an impact on the home advantage in different leagues around the world, and if they did, to what extent. Individual game data from the past 10 seasons were used for analysis of both the NBA and the Premier League. The results show that there is a significant difference in win percentage between prior seasons and seasons behind closed doors. In addition to win percentage, many other game statistics see a significant shift as well. Overall, the significance of being the home team disappears in games following the COVID-19 break.
Created predictive models using R to determine significant variables that help determine whether someone will default on their loans using a data set of almost 900,000 loan applicants.
Corporate buzzword terms like “big data” and “data analytics” are vague in meaning, and are thrown around by media sources often enough to obfuscate their actual meanings. These concepts are then associated with company-wide initiatives beyond the reach of the individual, in a nebulous world where people know that analytics happens, but don’t understand what it is.
The power of data analytics is not reserved for company-wide initiatives, or only employed by Silicon Valley tech start-ups. Its impacts are visible down at the team or department level, and can be conducted by the individual employees. The field of data analytics is evolving, and within it exists a rapid transition in which the individual employee is becoming a source for insight and value creation through the adoption of analytics based approaches.
The purpose of this thesis is to showcase an example of this claim, and demonstrate how an analytics based approach was applied to an existing accounting process to create new insights and information. To do this, I will discuss my development of an Excel based Dashboard Analytics tool, which I completed during my internship with Bechtel Corporation throughout the summer of 2018, and I will use this analytics tool to demonstrate the improvements that small-scale analytics had on a pre-existing process. During this discussion, I will address conceptual aspects of database design that related to my project, and will show how I applied this classroom learning to a working environment. The paper will begin with an overview of the desired goals of the group in which I was based, and will then analyze how the needs of the group led to the creation and implementation of this new analytics-based reporting tool. I will conclude with a discussion of the potential future use of this tool, and how the inclusion of these analytical approaches will continue to shape the working environment.
The goal of this project is to develop a deeper understanding of how machine learning pertains to the business world and how business professionals can capitalize on its capabilities. It explores the end-to-end process of integrating a machine and the tradeoffs and obstacles to consider. This topic is extremely pertinent today as the advent of big data increases and the use of machine learning and artificial intelligence is expanding across industries and functional roles. The approach I took was to expand on a project I championed as a Microsoft intern where I facilitated the integration of a forecasting machine learning model firsthand into the business. I supplement my findings from the experience with research on machine learning as a disruptive technology. This paper will not delve into the technical aspects of coding a machine model, but rather provide a holistic overview of developing the model from a business perspective. My findings show that, while the advantages of machine learning are large and widespread, a lack of visibility and transparency into the algorithms behind machine learning, the necessity for large amounts of data, and the overall complexity of creating accurate models are all tradeoffs to consider when deciding whether or not machine learning is suitable for a certain objective. The results of this paper are important in order to increase the understanding of any business professional on the capabilities and obstacles of integrating machine learning into their business operations.
sports, banking, and other disciplines. We use predictive analytics and modeling to
determine the impact of certain factors that increase the probability of a successful
fourth down conversion in the Power 5 conferences. The logistic regression models
predict the likelihood of going for fourth down with a 64% or more probability based on
2015-17 data obtained from ESPN’s college football API. Offense type though important
but non-measurable was incorporated as a random effect. We found that distance to go,
play type, field position, and week of the season were key leading covariates in
predictability. On average, our model performed as much as 14% better than coaches
in 2018.
