Business Commons^™

Airbnb Valuation: A Machine Learning Approach, Katherine Wyatt

Graduate Theses and Dissertations

This thesis uses a geospatially-enhanced, machine learning approach to investigate variations in rental success on the peer-to-peer property sharing website Airbnb.com. Geographic factors, listing attributes and amenities, customer response metrics, and host attributes are included in decision tree modeling to predict the short-term probability of receiving a review. The most important variables in increasing model accuracy are assessed and variations in the importance of these variables investigated using Shapley values.

Improving Credit Card Fraud Detection Using Transfer Learning And Data Resampling Techniques, Charmaine Eunice Mena Vinarta

Electronic Theses, Projects, and Dissertations

This Culminating Experience Project explores the use of machine learning algorithms to detect credit card fraud. The research questions are: Q1. What cross-domain techniques developed in other domains can be effectively adapted and applied to mitigate or eliminate credit card fraud, and how do these techniques compare in terms of fraud detection accuracy and efficiency? Q2. To what extent do synthetic data generation methods effectively mitigate the challenges posed by imbalanced datasets in credit card fraud detection, and how do these methods impact classification performance? Q3. To what extent can the combination of transfer learning and innovative data resampling techniques …

Secondary Features Of Importance For A Url Ranking, Atajan Abdyyev

Dissertations and Theses

This paper investigates the impact of secondary ranking factors on webpage relevance and rankings in the context of Search Engine Optimization (SEO), focusing on the jewelry domain within the United States e-commerce market. By generating a keyword list related to jewelry and retrieving top URLs from Google's search results, the study employs machine learning models including XGBoost, CatBoost, and Linear Regression to identify key features influencing webpage relevance and rankings.The findings highlight specific optimal ranges for features like Outlinks, Unique Inlinks, Flesch Reading Ease Score, and others, indicating their significant impact on better rankings. Notably, Random Forest model performed best …

Statistical Analysis And Machine Learning To Improve League Championship Series Teams, Alexander Gilles

Electronic Theses, Projects, and Dissertations

ABSTRACT

One area for further study in Esports is the use of advanced analytics from a performance standpoint. This culminating experience project sought to find and implement effective performance analytics techniques, using the most popular Esport (League of Legends) as its subject. The research questions asked are (Q1) How do champions, players, and their associated in-game variables impact the results of League of Legends matches? (Q2) How can machine learning algorithms be implemented to utilize descriptive and predictive analytics for League of Legends most effectively? Additionally, while not an element of the analysis and machine learning model, it is important …

Using Machine Learning Techniques To Model Encoder/Decoder Pair For Non-Invasive Electroencephalographic Wireless Signal Transmission, Ernst Fanfan

Master of Science in Computer Science Theses

This study investigated the application and enhancement of Non-Invasive Brain-Computer Interfaces (NI-BCIs), focused on enhancing the efficiency and effectiveness of this technology for individuals with severe physical limitations. The core research goal was to improve current limitations associated with wires, noise, and invasive procedures often associated with BCI technology. The key discussed solution involves developing an optimized Encoder/Decoder (E/D) pair using machine learning techniques, particularly those borrowed from Generative Adversarial Networks (GAN) and other Deep Neural Networks, to minimize data transmission and ensure robustness against data degradation. The study highlighted the crucial role of machine learning in self-adjusting and isolating …

The Rise Of Text Analysis: Using Machine Learning To Explain The Variation In Going Concern Accuracy, Yimei Zhang

USF Tampa Graduate Theses and Dissertations

Auditors are required to issue modified audit opinions if they have sufficient doubts about the client’s ability to continue as a going concern. These going concern opinions represent an important information resource for financial statement users to evaluate client performance, and are associated with a number of negative capital market outcomes (e.g. negative returns, increased cost of capital, etc.). Despite being used by capital market participants, going concern opinions are commonly plagued with Type I errors (false positive) and Type II errors (false negative), making them a particularly noisy measure. The purpose of this study is to determine whether machine …

Accounting And Financial Statements Auto Analysis System, Zhen Jia

Electronic Theses, Projects, and Dissertations

This project was motivated by the need to revolutionize the generation of financial statements and financial analysis process thus speeding up business decision making. The research questions were: 1) How can machine learning increase the speed of financial statement preparation and automate financial statements analysis? 2) How can businesses balance the benefits of automating financial analysis with potential concerns around privacy, data security, and bias? 3) Can the Java J2EE framework provide a reliable running environment for machine learning?

The findings were: 1) Machine learning can significantly increase the accuracy and speed of financial analysis. Using machine learning algorithms, financial …

A Systematic Literature Review Of Ransomware Attacks In Healthcare, Jasler Klien Adlaon

Electronic Theses, Projects, and Dissertations

This culminating experience project conducted a Systematic Literature Review of ransomware in the healthcare industry. Due to COVID-19, there has been an increase in ransomware attacks that took healthcare by surprise. Although ransomware is a common attack, the current healthcare infrastructure and security mechanisms could not suppress these attacks. This project identifies peer-viewed literature to answer these research questions: “What current ransomware attacks are used in healthcare systems? “What ransomware attacks are likely to appear in the future?” and “What solutions or methods have been used to prepare, prevent, and recover from these attacks?” The purpose of this research is …

The Impact Of Case Management Intervention For Insured Asthma Patients In Louisiana, An Empirical Study, Mohamed Mohamed Ohaiba

LSU Doctoral Dissertations

Asthma is a chronic condition whose symptoms are managed/prevented using medication and interventions. The overarching objective of this study was to evaluate the impact of patients' demographics on case management enrollment and healthcare utilization, as well as to develop machine learning models to predict high-cost patients.

To accomplish these goals, the Man-Whiteness test, the chi-squares test, logistic regression and odds ratios, and machine learning models were implemented. The average cost of the non-enrolled CM group was significantly higher than the enrolled group (p-value .0001). In addition, the non-enrolled groups had considerably more visits to the emergency department than the other …

Pict-Dpa: A Quality-Compliance Data Processing Architecture To Improve The Performance Of Integrated Emergency Care Clinical Decision Support System, Ruizhi Yu

CGU Theses & Dissertations

Emergency Care System (ECS) is a critical component of health care systems by providing acute resuscitation and life-saving care. As a time-sensitive care operation system, any delay and mistake in the decision-making of these EC functions can create additional risks of adverse events and clinical incidents. The Emergency Care Clinical Decision Support System (EC-CDSS) has proven to improve the quality of the aforementioned EC functions. However, the literature is scarce on how to implement and evaluate the EC-CDSS with regard to the improvement of PHOs, which is the ultimate goal of ECS. The reasons are twofold: 1) lack of clear …