Matching Items (20)
Filtering by

Clear all filters

133924-Thumbnail Image.png
Description
Sagebrush Coffee is a small business in Chandler, Arizona that purchases green beans, roasts them in small batches for quality, and ships fresh, gourmet roasted coffee beans across the nation. Deciding which coffee beans to buy and roast is one of the most crucial business decisions Sagebrush and other gourmet

Sagebrush Coffee is a small business in Chandler, Arizona that purchases green beans, roasts them in small batches for quality, and ships fresh, gourmet roasted coffee beans across the nation. Deciding which coffee beans to buy and roast is one of the most crucial business decisions Sagebrush and other gourmet coffee roasters face. Further complicating this decision is the fact that coffee is a crop, and like all crops, has a specific growing season and the exact same product cannot usually be ordered from year to year, even if it proves to be successful. The goal of this research is to use data analytics and visualization to help Sagebrush make better purchasing decisions by identifying consumer purchasing trends and providing a recommendation for their portfolio mix. In the end, I found that Latin American coffees are popular with both returning and first-time customers, but a specific country of origin does not appear to be associated with the top coffee producing countries. Additionally, December is a critical month for Sagebrush and Sagebrush should make sure to target the states with the most sales: California, Pennsylvania, and New York. Arizona has growth potential as it is not one of the top three locations, despite the presence of a physical store. Also included in the following report is a portfolio recommendation suggesting how many of each product based on region, processing type, and roast level to carry in inventory.
ContributorsBlue, Jessica Morgan (Author) / Kellso, James (Thesis director) / Davila, Eddie (Committee member) / Department of Information Systems (Contributor) / Economics Program in CLAS (Contributor) / Department of Supply Chain Management (Contributor) / Morrison School of Agribusiness (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
135558-Thumbnail Image.png
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 media as a platform. The data spans the period of September 2015 to March 2016, which was during the primary

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.
ContributorsMortimer, Schuyler Kenneth (Author) / Simon, Alan (Thesis director) / Mousavi, Seyedreza (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
133184-Thumbnail Image.png
Description
Cryptocurrencies are notorious for its volatility. But with its incredible rise in price, Bitcoin keep being on the top among the trending topics on social media. Although doubts continue to rise with price, Bloomberg even make critics on Bitcoin as ‘the biggest bubble in the history’, some investors still hold

Cryptocurrencies are notorious for its volatility. But with its incredible rise in price, Bitcoin keep being on the top among the trending topics on social media. Although doubts continue to rise with price, Bloomberg even make critics on Bitcoin as ‘the biggest bubble in the history’, some investors still hold strong enthusiasm and confidence towards Bitcoin. As contradicting opinions increase, it is worthy to dive into discussions on social media and use a scientific method to evaluate public’s non-negligible role in crypto price fluctuation.

Sentiment analysis, which is a notably method in text mining, can be used to extract the sentiment from people’s opinion. It then provides us with valuable perception on a topic from the public’s attitude, which create more opportunities for deeper analysis and prediction.

The thesis aims to investigate public’s sentiment towards Bitcoin through analyzing 10 million Bitcoin related tweets and assigning sentiment points on tweets, then using sentiment fluctuation as a factor to predict future crypto fluctuation. Price prediction is achieved by using a machine learning model called Recurrent Neural Network which automatically learns the pattern and generate following results with memory. The analysis revels slight connection between sentiment and crypto currency and the Neural Network model showed a strong connection between sentiment score and future price prediction.
ContributorsZhu, Xiaoyu (Author) / Benjamin, Victor (Thesis director) / Qinglai, He (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
137296-Thumbnail Image.png
Description
This thesis studies the area of sentiment analysis and its general uses, benefits, and limitations. Social networking, blogging, and online forums have turned the Web into a vast repository of comments on many topics. Sentiment analysis is the process of using software to analyze social media to gauge the attitudes

This thesis studies the area of sentiment analysis and its general uses, benefits, and limitations. Social networking, blogging, and online forums have turned the Web into a vast repository of comments on many topics. Sentiment analysis is the process of using software to analyze social media to gauge the attitudes or sentiments of the users/authors concerning a particular subject. Sentiment analysis works by processing (data mining) unstructured textual evidence using natural language processing and machine learning to determine a positive, negative, or neutral measurement. When utilized correctly, sentiment analysis has the potential to glean valuable insights into consumers' minds, which in turn leads to increased revenue and improved customer satisfaction for businesses. This paper looks at four industries in which sentiment analysis is being used or being considered: retail/services, politics, healthcare, and finances. The goal of the thesis will be to explore whether sentiment analysis has been used successfully for economic or social benefit and whether it is a practical solution for analyzing consumer opinion.
ContributorsSoumya, Saswati (Author) / Uday, Kulkarni (Thesis director) / Brooks, Daniel (Committee member) / Barrett, The Honors College (Contributor) / Department of Economics (Contributor) / WPC Graduate Programs (Contributor) / Department of Information Systems (Contributor)
Created2014-05
136992-Thumbnail Image.png
Description
Monocular is a user engagement application that offers a website owner the opportunity to track user behavior and use the data to better understand the site's strengths and weaknesses in terms of user satisfaction and motivation. This data allows the customer to make improvements to a website, resulting in a

Monocular is a user engagement application that offers a website owner the opportunity to track user behavior and use the data to better understand the site's strengths and weaknesses in terms of user satisfaction and motivation. This data allows the customer to make improvements to a website, resulting in a better user experience and potential for an improved bottom line.
ContributorsHooke, Wade (Co-author) / Ortiz-Monasterio, Diego (Co-author) / Clark, Joseph (Thesis director) / Prince, Linda (Committee member) / Barrett, The Honors College (Contributor) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / W. P. Carey School of Business (Contributor)
Created2014-05
133499-Thumbnail Image.png
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 paper investigates four forms of public services (schools, libraries, fire stations, and police stations), first by researching the background of

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.
ContributorsNorbury, Adam Charles (Author) / Simon, Alan (Thesis director) / Simon, Phil (Committee member) / Department of Information Systems (Contributor) / Department of English (Contributor) / Department of Economics (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
134373-Thumbnail Image.png
Description
Our research encompassed the prospect draft in baseball and looked at what type of player teams drafted to maximize value. We wanted to know which position returned the best value to the team that drafted them, and which level is safer to draft players from, college or high school. We

Our research encompassed the prospect draft in baseball and looked at what type of player teams drafted to maximize value. We wanted to know which position returned the best value to the team that drafted them, and which level is safer to draft players from, college or high school. We decided to look at draft data from 2006-2010 for the first ten rounds of players selected. Because there is only a monetary cap on players drafted in the first ten rounds we restricted our data to these players. Once we set up the parameters we compiled a spreadsheet of these players with both their signing bonuses and their wins above replacement (WAR). This allowed us to see how much a team was spending per win at the major league level. After the data was compiled we made pivot tables and graphs to visually represent our data and better understand the numbers. We found that the worst position that MLB teams could draft would be high school second baseman. They returned the lowest WAR of any player that we looked at. In general though high school players were more costly to sign and had lower WARs than their college counterparts making them, on average, a worse pick value wise. The best position you could pick was college shortstops. They had the trifecta of the best signability of all players, along with one of the highest WARs and lowest signing bonuses. These were three of the main factors that you want with your draft pick and they ranked near the top in all three categories. This research can help give guidelines to Major League teams as they go to select players in the draft. While there are always going to be exceptions to trends, by following the enclosed research teams can minimize risk in the draft.
ContributorsValentine, Robert (Co-author) / Johnson, Ben (Co-author) / Eaton, John (Thesis director) / Goegan, Brian (Committee member) / Department of Finance (Contributor) / Department of Economics (Contributor) / Department of Information Systems (Contributor) / School of Accountancy (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
133988-Thumbnail Image.png
Description
The National Basketball Association is the world's most recognized professional basketball league. Athletes such as Kobe Bryant and Lebron James have transcended from being high school standouts to global icons, but their careers might not have panned out the same way if they weren't allowed to declare for the draft

The National Basketball Association is the world's most recognized professional basketball league. Athletes such as Kobe Bryant and Lebron James have transcended from being high school standouts to global icons, but their careers might not have panned out the same way if they weren't allowed to declare for the draft immediately upon graduating high school. In 2005, the NBA and the NBA Players Association agreed to implement an age limit for athletes declaring for the NBA Draft. Although this was supposed to reduce the quantity of younger players declaring for the draft, the rule has been ineffective as the average age of lottery picks, also known as the first 14 picks of the draft, has decreased since the rule's implementation. Adam Silver, the current commissioner of the NBA, has been vocal about potentially raising the minimum draft-eligible age once more because of NBA team executives calling recent draft picks unfit for the NBA. The purpose of this research is to examine if lottery picks are indeed "NBA ready" upon being drafted, and if there is a correlation between the age at which they are drafted, the pick at which they were selected, the length of their career, and their career success. Various statistical analysis techniques are utilized, such as the calculation of R-squared values and correlation coefficients, and the usage of t-tests and multiple regressions. Box score statistics such as minutes per game, points per game, rebounds, and assists as well as advanced metrics such as player efficiency rating, win shares, box plus/minus, and value over replacement player were the focal point of this study. Players drafted with lottery selections from the 1985-2016 drafts had their career statistics compiled and examined for this analysis in order to adequately conduct the regressions. The results indicate that although lottery picks are having a decreasing immediate impact upon being drafted, the younger an athlete is drafted, the more long-term success they can expect to achieve in the NBA.
ContributorsKender, Mitchell Edward (Author) / McIntosh, Daniel (Thesis director) / Eaton, John (Committee member) / Department of Information Systems (Contributor) / Department of Marketing (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
135074-Thumbnail Image.png
Description
Data is ever present in the world today. Data can help predict presidential elections, Super Bowl champions, and even the weather. However, it's very hard, if not impossible, to predict how people feel unless they tell us. This is when impulse spending with data comes in handy. Companies are constantly

Data is ever present in the world today. Data can help predict presidential elections, Super Bowl champions, and even the weather. However, it's very hard, if not impossible, to predict how people feel unless they tell us. This is when impulse spending with data comes in handy. Companies are constantly looking for ways to get honest feedback when they are doing market research. Often, the research obtained ends up being unreliable or biased in some way. Allowing users to make impulse purchases with survey data is the answer. Companies can still gather the data that they need to do market research and customers can get more features or lives for their favorite games. It becomes a win-win for both users and companies. By adding the option to pay with information instead of money, companies can still get value out of frugal players. Established companies might not care so much about the impulse spending for purchases made in the application, however they would find a great deal of value in hearing about what customers think of their product or upcoming event. The real value from getting data from customers is the ability to train analytics models so that companies can make better predictions about consumer behavior. More accurate predictions can lead to companies being better prepared to meet the needs to the customer. Impulse spending with data provides the foundation to creating a software that can create value from all types of users regardless of whether the user is willing to spend money in the application.
ContributorsYotter, Alexandria Lee (Author) / Olsen, Christopher (Thesis director) / Sopha, Matthew (Committee member) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
134845-Thumbnail Image.png
Description
The purpose of this thesis was to develop a tool to provide information and data for design teams to use throughout the mobile application design process. Ideally, this would enable teams to see patterns in iterative design, and ultimately use data-driven analysis to make their own decisions. The initial problem

The purpose of this thesis was to develop a tool to provide information and data for design teams to use throughout the mobile application design process. Ideally, this would enable teams to see patterns in iterative design, and ultimately use data-driven analysis to make their own decisions. The initial problem was a lack of available information offered by mobile application design teams—the initial goal being to work closely with design teams to learn their decision-making methodology. However, every team that was reached out to responded with rejection, presenting a new problem: a lack of access to quality information regarding the decision-making process for mobile applications. This problem was addressed by the development of an ethical hacking script that retrieves reviews in bulk from the Google Play Store using Python. The project was a success—by feeding an application’s unique Play Store ID, the script retrieves a user-specified amount of reviews (up to millions) for that mobile application and the 4 “recommended” applications from the Play Store. Ultimately, this thesis proved that protected reviews on the Play Store can be ethically retrieved and used for data-driven decision making and identifying patterns in an application’s iterative design. This script provides an automated tool for teams to “put a finger on the pulse” of their target applications.
ContributorsDyer, Mitchell Patrick (Author) / Lin, Elva (Thesis director) / Giles, Charles (Committee member) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12