Matching Items (2)
Filtering by

Clear all filters

147645-Thumbnail Image.png
Description

We attempted to apply a novel approach to stock market predictions. The Logistic Regression machine learning algorithm (Joseph Berkson) was applied to analyze news article headlines as represented by a bag-of-words (tri-gram and single-gram) representation in an attempt to predict the trends of stock prices based on the Dow Jones

We attempted to apply a novel approach to stock market predictions. The Logistic Regression machine learning algorithm (Joseph Berkson) was applied to analyze news article headlines as represented by a bag-of-words (tri-gram and single-gram) representation in an attempt to predict the trends of stock prices based on the Dow Jones Industrial Average. The results showed that a tri-gram bag led to a 49% trend accuracy, a 1% increase when compared to the single-gram representation’s accuracy of 48%.

ContributorsBarolli, Adeiron (Author) / Jimenez Arista, Laura (Thesis director) / Wilson, Jeffrey (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
We created a sufficient database that can be used by the SDA for extensive analysis as well as a starting foundation for further development. The design of the database revolved around the men’s basketball team and includes data for conferences, teams, players, and the historic schedule of teams past performances.

We created a sufficient database that can be used by the SDA for extensive analysis as well as a starting foundation for further development. The design of the database revolved around the men’s basketball team and includes data for conferences, teams, players, and the historic schedule of teams past performances. This design can be used as a template for future sports that would like to be added to the database. The queries we ran that tested the functionality of the database show the utility and accessibility that is possible with the data currently in the database. The visuals included assist our examples by exhibiting how the results gathered by the queries can be transformed into figures that may be more visually appealing than the raw data. We came up with example questions that could be potential questions the SDA may have regarding current and past performance statistics. We expect that as a continuation of this project, the SDA will be able to utilize it to their advantage to analyze and improve the performance levels of other teams.
ContributorsSundar, Mayuri (Co-author) / Adusei, Evans (Co-author) / Consalvo, Joshua (Co-author) / Saunders, Wyatt (Co-author) / Wilson, Zechariah (Co-author) / Moser, Kathleen (Thesis director) / Wilson, Jeffrey (Committee member) / School of Social Transformation (Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05