Matching Items (972)
- Creators: Computer Science and Engineering Program
- Creators: Department of Supply Chain Management
- Member of: Barrett, The Honors College Thesis/Creative Project Collection
This project aims to incorporate the aspect of sentiment analysis into traditional stock analysis to enhance stock rating predictions by applying a reliance on the opinion of various stocks from the Internet. Headlines from eight major news publications and conversations from Yahoo! Finance’s “Conversations” feature were parsed through the Valence Aware Dictionary for Sentiment Reasoning (VADER) natural language processing package to determine numerical polarities which represented positivity or negativity for a given stock ticker. These generated polarities were paired with stock metrics typically observed by stock analysts as the feature set for a Logistic Regression machine learning model. The model was trained on roughly 1500 major stocks to determine a binary classification between a “Buy” or “Not Buy” rating for each stock, and the results of the model were inserted into the back-end of the Agora Web UI which emulates search engine behavior specifically for stocks found in NYSE and NASDAQ. The model reported an accuracy of 82.5% and for most major stocks, the model’s prediction correlated with stock analysts’ ratings. Given the volatility of the stock market and the propensity for hive-mind behavior in online forums, the performance of the Logistic Regression model would benefit from incorporating historical stock data and more sources of opinion to balance any subjectivity in the model.
Comparative Evaluation of Generative Machine Learning Models for Jazz Improvisation using Numerical Metrics
Standardization is sorely lacking in the field of musical machine learning. This thesis project endeavors to contribute to this standardization by training three machine learning models on the same dataset and comparing them using the same metrics. The music-specific metrics utilized provide more relevant information for diagnosing the shortcomings of each model.
The purpose of this project was to examine the retail grocery industry in the United States. Focusing on three highly successful regional grocery chains, I used primary and secondary research to determine if these chains should expand nationwide for increased revenue and profitability.
The pandemic that hit in 2020 has boosted the growth of online learning that involves the booming of Massive Open Online Course (MOOC). To support this situation, it will be helpful to have tools that can help students in choosing between the different courses and can help instructors to understand what the students need. One of those tools is an online course ratings predictor. Using the predictor, online course instructors can learn the qualities that majority course takers deem as important, and thus they can adjust their lesson plans to fit those qualities. Meanwhile, students will be able to use it to help them in choosing the course to take by comparing the ratings. This research aims to find the best way to predict the rating of online courses using machine learning (ML). To create the ML model, different combinations of the length of the course, the number of materials it contains, the price of the course, the number of students taking the course, the course’s difficulty level, the usage of jargons or technical terms in the course description, the course’s instructors’ rating, the number of reviews the instructors got, and the number of classes the instructors have created on the same platform are used as the inputs. Meanwhile, the output of the model would be the average rating of a course. Data from 350 courses are used for this model, where 280 of them are used for training, 35 for testing, and the last 35 for validation. After trying out different machine learning models, wide neural networks model constantly gives the best training results while the medium tree model gives the best testing results. However, further research needs to be conducted as none of the results are not accurate, with 0.51 R-squared test result for the tree model.
This creative project is a short story in the Gothic genre followed by an explanation of certain literary elements and decisions. The Gothic genre often explores supernatural and uncomfortable topics that can challenge the reader’s perception and understanding of the world. Through this means of storytelling, authors are given the opportunity to connect the supernatural with complex and sensitive topics that may be difficult or even taboo to speak about in certain locations and time periods. In this thesis, I embrace the traditions of the Gothic-genre with a story that focuses on the issues prevalent today. The years 2020 and 2021 have been unprecedented times for humanity. Technology continues to grow at an alarming rate, suicide rates of young people have been on the rise for years, and a global pandemic has people adapting to all new ways of living. During these ever changing times, it is the Gothic that may provide guidance through these uncertainties by shedding light on the problems that will plague humanity both today and tomorrow. The story follows an outcast from society who aids in the creation of a divine monster, and the consequences that follow.
In response to the Bosnian and Rwandan genocides of the 1990’s, the United Nations created the Responsibility to Protect (R2P) doctrine as part of its 2005 World Summit Outcome document. The goal of R2P is to promote the idea that the international community should act to protect populations from mass atrocity crimes (genocide, crimes against humanity, war crimes, and ethnic cleansing) in the case a State fails to meet their responsibility. This report seeks to examine the Responsibility to Protect principle and see how its concepts are perceived and implemented in the private sector, given the sector’s significant influence in the world today. Using R2P as a frame of reference, I explored the concept that private sector organizations, through their actions and operations, have a responsibility to not profit from or enable systems that perpetuate mass atrocity crimes against populations. This was done through an analysis of private sector firms, regulatory frameworks, industry norms, organization initiatives, and perspectives of actors engaging with the subject matter, in addition to a modern case study regarding the experience of Uighurs and Turkic Muslims in Xinjiang, China. The scope of this project was focused on select American companies that are multinational publicly traded companies with a market capitalization of over $200 billion. This report is meant to serve as a guide for into the concepts of R2P in the private sector and provides access to resources for further exploration.
IoT Allocation Methodology: Allocation Methodology for Indirect Research and Development Costs for Internet of Things Products
While a fairly new concept, Internet of Things (IoT) has become an important part of the business structure and operating segments of many technology companies in the last decade. IoT refers to the evolution of devices that, connected to the internet, can share and integrate information, becoming an always-growing intelligent system of systems. As a leader in the semiconductor industry, Company X and its growing IoT division, have constant new challenges and opportunities given the complexity of the IoT field. The business model employed by the IoT division includes adopting and modifying existing technologies and products from its sister groups within Company X. Since these products are being leveraged by the IoT division, it makes indirect research and development allocation for said products much more complex. This thesis will address how the IoT division at Company X can approach this problem in the most beneficial way for the division and company as a whole through the analysis of two allocation methodologies: percentage of revenue (Allocation Basis 1) and percentage of direct research and development (Allocation Basis 2).
Since the onset of the COVID-19 pandemic, the world has been turned upside down. People everywhere are recommended to self-isolate and social distance to limit the spread of the deadly virus. Older adults specifically are being forced into isolation because they are at the highest risk for severe illness—illness that can result in hospitalization, intensive care, or even death. But this isolation is not new. Even before COVID-19, the older adult population has been suffering through a social isolation epidemic. And now, with social distancing measures in place, even more adults are being socially isolated to remain safe and healthy. But when individuals are isolated for long periods of time and no longer have an active social network to connect with, this social isolation can become harmful. Social isolation is known to increase the risk of cardiovascular disease, obesity, and stroke, and it is associated with anxiety, depression, and cognitive decline. Furthermore, the risk of premature death from any cause increases because of social isolation. With all these negative consequences, it is crucial that we confront the toll that COVID-19 countermeasures have taken on older adults and look for ways to prevent social isolation. Venture Together, a multi-user social media platform designed for older adults, attempts to do just this and more.
Th NTRU cryptosystem is a lattice-based encryption scheme. Several parameters determine the speed, size, correctness rate and security of the algorithm. These parameters need to be carefully selected for the algorithm to function correctly. This thesis includes a short overview of the NTRU algorithm and its mathematical background before discussing the results of experimentally testing various different parameter sets for NTRU and determining the effect that different relationships between these parameters have on the overall effectiveness of NTRU.
In 2022, the revenue generated from accounting services hit an all-time high of 119.48 billion USD (“Accounting Services in the US - Market Size”, 2022). On top of this, research has shown that 45% of all accounting professionals would like to automate something about their workflow (Thomas, 2020). Indeed, a lot of bookkeeping accountancy has been phased out by simple automation. However, larger accounting tasks like business mergers still require a team of accountants despite being a largely iterative process. This project chronicles one such attempt at automating accounting events or transactions that are performed by businesses both large and small. With the help of accounting students Madeline Stolper and Heddie Liu we were able to build a fully-functioning website to automate accounting transactions. For this project, we used industry-standard software frameworks React and Express to build the site with dynamic accounting applications. These applications were built with reusable components, making the development of future applications very simple. We also leveraged cutting-edge technological solutions from Amazon Web Services to make the website available on the Internet with rapid response times. Lastly, we incorporated an agile approach to project management and communication, in order to create functionality in the most efficient and organized manner possible. On a large scale, something like this has never been attempted and TurboIFRS/GAAP represents a revolutionary leap in accounting automation.