Matching Items (80)
Filtering by
- All Subjects: Machine Learning
- Creators: Computer Science and Engineering Program
Description
This thesis project focuses on the creation and assessment of the "Simple Stocks" app, a straightforward investment tool specifically developed for people who are new to investing and find it challenging to comprehend the complexities of the stock market. We identified a significant gap in the availability of easy-to-understand resources and information for beginner investors, which led us to design an app that provides clear and simple data, professional advice from financial analysts, and an advanced machine learning feature to predict stock trends. The "Simple Stocks" app also incorporates a voting feature, allowing users to see what other investors think about specific stocks. This functionality not only helps users make informed decisions but also encourages a sense of community, as users can learn from each other's experiences and opinions. By creating a supportive environment, the app promotes a more approachable and enjoyable experience for those who are new to investing. Following the successful release of the "Simple Stocks'' app on the App Store, our current objectives include expanding the user base and looking into various ways to generate income. One possible approach is to collaborate with other companies and establish an advertising-based revenue model, which would benefit both parties by attracting more users and increasing profits.
ContributorsBiyani, Saloni (Author) / Karuppiah, Meena (Co-author) / Kancherla, Sohan (Co-author) / Byrne, Jared (Thesis director) / Lee, Christopher (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05
Description
Energy poverty is a pressing issue in agricultural areas that affects the livelihoods of millions of people worldwide. The lack of access to modern energy services in rural communities hinders the development of the agricultural sector and limits economic opportunities. To address this issue, this thesis aims to develop a predictive modeling framework using machine learning techniques to identify feasible interventions that can improve energy access in specific rural agricultural regions.
Machine learning plays a pivotal role in addressing energy poverty in rural agricultural regions. By leveraging the power of advanced data analytics and predictive modeling, machine learning algorithms can analyze vast datasets related to energy usage, agricultural practices, geographic factors, and socioeconomic conditions. These algorithms can uncover valuable insights and patterns that are not readily apparent through traditional analytical methods. Moreover, machine learning enables the development of predictive models that can forecast energy demand and identify optimal strategies for improving energy access in rural areas. These models can take into account various variables, such as crop cycles, weather conditions, and community needs, to recommend interventions that are tailored to the specific requirements of each region.
ContributorsKonatam, Saisumana (Author) / Osburn, Steven (Thesis director) / Kerner, Hanah (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-12
Description
In this work, we explore the potential for realistic and accurate generation of hourly traffic volume with machine learning (ML), using the ground-truth data of Manhattan road segments collected by the New York State Department of Transportation (NYSDOT). Specifically, we address the following question– can we develop a ML algorithm that generalizes the existing NYSDOT data to all road segments in Manhattan?– by introducing a supervised learning task of multi-output regression, where ML algorithms use road segment attributes to predict hourly traffic volume. We consider four ML algorithms– K-Nearest Neighbors, Decision Tree, Random Forest, and Neural Network– and hyperparameter tune by evaluating the performances of each algorithm with 10-fold cross validation. Ultimately, we conclude that neural networks are the best-performing models and require the least amount of testing time. Lastly, we provide insight into the quantification of “trustworthiness” in a model, followed by brief discussions on interpreting model performance, suggesting potential project improvements, and identifying the biggest takeaways. Overall, we hope our work can serve as an effective baseline for realistic traffic volume generation, and open new directions in the processes of supervised dataset generation and ML algorithm design.
ContributorsOtstot, Kyle (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05
Description
In the age of information, collecting and processing large amounts of data is an integral part of running a business. From training artificial intelligence to driving decision making, the applications of data are far-reaching. However, it is difficult to process many types of data; namely, unstructured data. Unstructured data is “information that either does not have a predefined data model or is not organized in a pre-defined manner” (Balducci & Marinova 2018). Such data are difficult to put into spreadsheets and relational databases due to their lack of numeric values and often come in the form of text fields written by the consumers (Wolff, R. 2020). The goal of this project is to help in the development of a machine learning model to aid CommonSpirit Health and ServiceNow, hence why this approach using unstructured data was selected. This paper provides a general overview of the process of unstructured data management and explores some existing implementations and their efficacy. It will then discuss our approach to converting unstructured cases into usable data that were used to develop an artificial intelligence model which is estimated to be worth $400,000 and save CommonSpirit Health $1,200,000 in organizational impact.
ContributorsBergsagel, Matteo (Author) / De Waard, Jan (Co-author) / Chavez-Echeagaray, Maria Elena (Thesis director) / Burns, Christopher (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05
Description
This thesis serves as an experimental investigation into the potential of machine learning through attempting to predict the future price of a cryptocurrency. Through the use of web scraping, short interval data was collected on both Bitcoin and Dogecoin. Dogecoin was the dataset that was eventually used in this thesis due to its relative stability compared to Bitcoin. At the time of the data collection, Bitcoin became a much more frequent topic in the media and had more significant fluctuations due to it. The data was processed into consistent three separate, consistent timesteps, and used to generate predictive models. The models were able to accurately predict test data given all the preceding test data but were unable to autoregressively predict future data given only the first set of test data points. Ultimately, this project helps illustrate the complexities of extended future price prediction when using simple models like linear regression.
ContributorsMurwin, Andrew (Author) / Bryan, Chris (Thesis director) / Ghayekhloo, Samira (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-12
Description
The field of quantum computing is an exciting area of research that allows quantum mechanics such as superposition, interference, and entanglement to be utilized in solving complex computing problems. One real world application of quantum computing involves applying it to machine learning problems. In this thesis, I explore the effects of choosing different circuit ansatz and optimizers on the performance of a variational quantum classifier tasked with binary classification.
ContributorsHsu, Brightan (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-12
Description
The number of extreme wildfires is on the rise globally, and predicting the size of a fire will help officials make appropriate decisions to mitigate the risk the fire poses against the environment and humans. This study attempts to find the burned area of fires in the United States based on attributes such as time, weather, and location of the fire using machine learning methods.
ContributorsPrabagaran, Padma (Author, Co-author) / Meuth, Ryan (Thesis director) / McCulloch, Robert (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2022-12
Description
This study aims to combine the wisdom of crowds with ML to make more accurate stock price predictions for a select set of stocks. Different from prior works, this study uses different input elicitation techniques to improve crowd performance. In addition, machine learning is used to support the crowd. The influence of ML on the crowd is tested by priming participants with suggestions from an ML model. Lastly, the market conditions and stock popularity is observed to better understand crowd behavior.
ContributorsBhogaraju, Harika (Author) / Escobedo, Adolfo R (Thesis director) / Meuth, Ryan (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-12
Description
Phishing is one of most common and effective attack vectors in modern cybercrime. Rather than targeting a technical vulnerability in a computer system, phishing attacks target human behavioral or emotional tendencies through manipulative emails, text messages, or phone calls. Through PyAntiPhish, I attempt to create my own version of an anti-phishing solution, through a series of experiments testing different machine learning classifiers and URL features. With an end-goal implementation as a Chromium browser extension utilizing Python-based machine learning classifiers (those available via the scikit-learn library), my project uses a combination of Python, TypeScript, Node.js, as well as AWS Lambda and API Gateway to act as a solution capable of blocking phishing attacks from the web browser.
ContributorsYang, Branden (Author) / Osburn, Steven (Thesis director) / Malpe, Adwith (Committee member) / Ahn, Gail-Joon (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05
Description
In the field of botany, it is often necessary for plants to be identified based on their phenotypical characteristics, whether in person or using previously collected image samples. This work can be tedious and challenging for a human botanist to complete, as datasets can be large and several species of plants strongly resemble each other. Various machine learning techniques, both supervised and unsupervised, can address this task with varying degrees of accuracy and efficiency thanks to their ability to identify subtle patterns in data. The objective of this research is to both conduct a review of previous studies that measure the effectiveness of various machine learning methods for plant identification and to build and test various models to draw up a comparison of the accuracies and efficiencies of the set of techniques.
A review of the existing literature found that any of the studied machine learning techniques can yield a high level of accuracy when used in the correct situations and on a suitable dataset. The results gathered from the models built from this research show that all else being equal, complex convolutional neural networks perform the best on this task, yielding an accuracy of 85.4% on the larger dataset. The other models tested in descending order of accuracy on the same dataset are k-nearest neighbors, random forest, k-means clustering, and a decision tree classifier.
ContributorsOlsen, Laela (Author) / Carter, Lynn Robert (Thesis director) / Bhargav, Vishnu (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05