Computer Science Honors Theses
Betting Just Got Easier: The Power Of Machine Learning And Making PredictionsThere comes a time in your life when you have endeavored to place a wager, whether minuscule or astronomically immense the goal is to victoriously triumph. What if you knew the chances of you winning? In this project, I analyzed The Big Five European soccer leagues data where I predict the probability of what team will win using various machine learning techniques while answering questions to maximize the accuracy of my prediction. The project drives away from the rigorous concepts of numbers, with a visual representation of the analytics. This breaks away from the extensive data into a more conceptualized aspect of betting. Many Bettors bet based on favorites, is that a valid way to place a bet? The first phase of this project is creating a descriptive analysis for understanding the data, the second phase is diving into support vector machines, random forest, and Xgboost to organize data elements and standardize how the data elements relate to one another to answer questions pertaining to wager making. I will make use of PySpark to show distinction between supervised learning models. The complex components will follow a sequential design metric to understand correctly how to maximize your bet. The results will consist of a prototype web application with a descriptive analysis of my findings, this includes betting prediction on my data. Users will get a deep understanding on why the results presented as they did.
A Journal of the "Resume Adder" ApplicationThe computer science programming process has many different elements. From the software development life cycle, to the hands on implementation, to providing the user with the results they are looking for, the procedure has to not on complex, but precise. There have been many different writings related to the SDLC, but this document details the process that I used to design my application for user operation.