Digital Commons Network^™

Predicting Early Customer Inactivity In The Banking Sector Using Machine Learning: A Churn Prevention, Ivana Mc Fadden

ICT

Customer churn, when customers stop using a company’s services, is a challenge for the banking sector (Singh et al., 2023). High churn rates often signal poor customer experiences, resulting in revenue losses and increased costs to obtain new clients. Goyal and Srivastava (2015) stress that fostering loyalty through exceptional service and understanding customer needs is important for long-term retention.

This project aims to predict early customer inactivity, an indicator of churn, by using machine learning. Early identification of at-risk customers will allow banks to apply targeted interventions, reduce acquisition costs, and improve customer satisfaction (Singh et al., 2023). By analysing …

Using Machine Learning To Predict Credit Card Fraud, Pedro Henrique Das Chagas Morais

ICT

Credit card fraud poses a significant challenge to financial institutions, leading to substantial financial losses and declining customer trust. This project develops and evaluates machine learning models to detect fraudulent credit card transactions using a large, realistic synthetic dataset. Following data preprocessing, exploratory analysis, and class-balancing using SMOTE, four supervised models—Logistic Regression, Decision Tree, Random Forest, and XGBoost—were trained and compared. Performance was assessed using metrics suited to imbalanced classification, including AUC, Recall, Precision, F1-score, and Average Precision. Results show that XGBoost, particularly after hyperparameter optimisation, delivered the strongest performance (AUC 0.99, Recall 0.83, AP 0.70), outperforming other models and …

Fake News Detection Using Machine Learning Models., Anne Higgins

ICT

This project investigates the use of machine learning to detect fake news, addressing the societal and political challenges posed by the widespread dissemination of false and misleading information. Using automated classification techniques, the project analyses news content to predict the likelihood of intentional deception. The methodology follows the CRISP-DM framework, encompassing data preparation, model development, and evaluation. By leveraging machine learning, the study aims to support organisations, governments, and digital platforms in mitigating misinformation, while also considering ethical, interpretability, and strategic implications. The findings provide actionable insights for enhancing content moderation and reducing the influence of disinformation in digital media …

Data Analysis For Maintenance Reliability., Romulo Menezes Santos

ICT

This project explores the application of predictive maintenance (PdM) in modern manufacturing, highlighting its strategic role in reducing downtime, optimising resources, and improving operational efficiency. Traditional reactive and preventive maintenance approaches are insufficient for Industry 4.0 environments, where machine failures can cause significant financial and operational losses. By leveraging sensor data, historical performance records, and machine learning techniques, PdM enables early detection of potential equipment failures, allowing maintenance teams to act proactively. The approach not only enhances operational reliability and safety but also supports strategic decision-making, cost control, and competitive advantage in globalised manufacturing contexts.

Comparative Evaluation Of Ai-Generated Synthetic Data And Real-World Data Performance In Predictive Analytics., Corey Louise Hughes

ICT

There are growing restraints when it comes to Real World Data (RWD), these include topics such as privacy regulations, ethical concerns, and the cost of collecting the data, and they have drove an interest in AI-generated synthetic data as a potential alternative in predictive analytics. This project examines the possibilities of synthetic data and if it can act as a reliable substitute for RWD in predictive modelling. This project uses Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic reproductive health data and evaluates its predictive performance against RWD using linear regression and key metrics, including Mean Absolute …

Efficient Evaluation Of Nala In Convlstm For High-Dimensional Time-Series Traffic-Flow Forecasting ., Sergej Sisov

ICT

Accurate traffic congestion prediction is essential for effective urban mobility and energy-efficient transport planning. This study evaluates the impact of optimizers on ConvLSTM models for short-term traffic forecasting using the METR-LA dataset, incorporating weather and event data as exogenous features. Two optimizers—Adam and Nesterov-accelerated Lookahead (NALA)—are compared under a frozen-T evaluation to prevent temporal leakage. Data preprocessing included five-minute alignment of weather data and event integration based on sensor proximity. Results show that the best-performing model (Variant C-2), integrating traffic, weather, and event features with reduced dropout and NALA optimization, achieved an MAE of 5.22 and RMSE of 8.79, outperforming …

Identifying And Forecasting Key Drivers Of Greenhouse Gas Emissions In Ireland's Residential Sector Multivariate Time Series Analysis., Sallam Noor Aldeen Salman

ICT

This study evaluates advanced time-series forecasting models to predict greenhouse gas emissions (GHGE) in Ireland's residential sector. LSTM, XGBoost, and ARIMA models were tested alongside feature selection methods including PCA, XGBoost-based importance, and Granger causality. Urban population growth and electricity consumption emerged as the most significant predictors. While LSTM struggled due to limited data, XGBoost showed strong predictive performance (MAPE ~9%), and ARIMA with key features achieved the highest accuracy (MAPE 3.78%). Forecasts indicate a declining GHGE trend, offering actionable insights for environmental planning and policy in the residential sector.

Identifying Skills Gaps And Labour Market Trends Using Machine Learning: A Data Analysis Of Tendencies Within The Irish Online Job Market., Stephen Ray

ICT

The Irish labour market is a dynamic system characterised by overlapping and distinct demands. The skills required to maintain competitiveness within today's labour market are constantly evolving in response to the needs of corporations, non-governmental organisations, and capital. Labour market participants, fulfilling specific roles, contribute to a skill-based relationship where supply and demand operates in new and innovative ways. With the advent of the internet, the labour market has shifted towards a digital environment, leading to the rise of online job advertisement platforms that cater to geographically defined regions. These platforms attract vast numbers of users and prospective employees daily …

Forecasting Hourly Police Call For Service Volumes: A Comparative Analysis Of Statistical, Machine Learning And Neural Network Models For Operational Planning., Patrick Duggan

ICT

Accurate demand forecasting is critical in operational settings where resource allocation and planning decisions depend on anticipated service volumes. Transactional systems that capture timestamped records provide valuable data sources for developing demand forecasts. This study examines hourly call volume forecasting using New Orleans police calls for service data, comparing the performance of statistical models, tree-based methods, and recurrent neural networks.

The research evaluates four primary modelling approaches: ARIMA models representing traditional statistical methods, XGBoost and Random Forest as a tree-based ensemble technique, and Gated Recurrent Units (GRUs) as deep learning alternatives. A naive seasonal model serves as the baseline benchmark. …

Predictive Analysis Of Atlantic Meridional Overturning Circulation Amoc And Its Climatic Implications On Ireland Using Advanced Machine Learning Techniques., Corey Whyte

ICT

The Atlantic Meridional Overturning Circulation (AMOC) plays a key role in regulating climate across the North Atlantic, including Ireland. This study analyses AMOC variability using RAPID, ODYSSEA, and MÉRA datasets to examine relationships between subsurface ocean conditions, sea surface temperatures, and air temperature. ARIMA/SARIMA models identify trends and correlations, while a Long Short-Term Memory (LSTM) neural network forecasts future climate changes. Results show rising sea surface temperatures, moderate links between salinity and temperature, and seasonal air temperature patterns with a slight upward trend. The LSTM model outperforms traditional statistical approaches in capturing complex patterns, highlighting the value of machine learning …

Tour Demand Forecasting In Ireland: Development And Evaluation Of Classical, Deep Learning, And Hybrid Models, Ruben Elias Charleston Montfort

ICT

Tourism plays a significant role in global economies by supporting employment, infrastructure, and national development. As international travel continues to grow, accurate tourism demand forecasting has become increasingly important for effective planning and decision-making. In Ireland, tourism is a key economic sector attracting millions of visitors annually. For tour operators such as Irish Day Tours, reliable demand forecasting is essential for optimizing logistics, resource allocation, marketing strategies, and customer satisfaction. Advances in machine learning and deep learning techniques offer new opportunities to improve forecasting accuracy and support data-driven decision-making within the tourism industry.

Sonic Photovoice And Critical Literacy: Listening To And Sounding What Is Me, What Is Not Me, And What Is Between, Alexander Chadwell

Theses and Dissertations--Curriculum and Instruction

This study examined sonic photovoice, a sound-based arts research method, as a tool for developing critical literacy in middle and high school students. Participants found and recorded sounds related to three categories, “what is me,” “what is not me,” and “what is between,” composed a sound collage using the sounds, and reflected on the experience. Framed by 4EA cognition, participatory sensemaking, and relational and everyday aesthetics, the study explored how listening and sounding shaped students’ conceptions of self and reality. Data from recordings, journals, and interviews suggest that the sonic engagement can foster relational, emergent understandings of self and …

Full Ride To College, But At What Cost?: Colonial Subjects At Imperial Educational Institutions In Binti And The Fifth Season, Martha Zornow

English Faculty Publications

A marginalized young person, often of a different physiognomy from those wielding power, sees the 'ivory tower' in her universe as a path to the learning, respect, power, and agency not available to her in her home environs. At their educational institutions, while their Blackness is not the basis for their outsider status, the Othering they experience mirrors that experienced by Black students at predominantly white universities in the real world. Theorizing the Colonial Role of Educational Institutions Following Thomas Macaulay's notorious' Minute on Education'(1835), educational systems have played a vital role in reaffirming the balance of power between the …

Welcoming Historically Under-Represented Groups In Higher Education Through Awareness Of Standard English Ideology, John Hellermann, Lynn Santelmann, Jennifer Mittelstaedt, Janet Cowal, Steven L. Thorne

Applied Linguistics Faculty Publications and Presentations

In the context of changing demographics at regional universities (including our own), we highlight an ongoing project at our university that addresses the last area of acceptable bias in English-medium higher education: bias against speakers of other languages and non-standard dialects of English. We discuss the hegemonic aspect of the Standard Academic English used by default at most US institutions of higher education and its role in potential discrimination against users of languages other than English and dialects other than the Standard. Data from over 2000 surveys, 55 follow up interviews, and three focus groups from faculty, staff and students …

Trees, Schools, & Stakeholders: Building Partnerships For Schoolyard Greening With Portland Urban Forestry Learning Landscapes, Claire Brase

Environmental Science and Management Professional Master's Project Reports

Portland Urban Forestry Learning Landscapes is a city program offering free tree planting and establishment services to schools, community groups, and multi-residential zones in the city of Portland, Oregon. This project report, completed on behalf of Learning Landscapes, uses qualitative evidence from interviews with school district administrators, teachers, volunteers, grounds staff, city employees, and outreach experts to gain a deeper understanding of the factors leading to successful collaboration between local school districts and their external community partners. These conversations with school and outreach personnel across the city suggest that district staff are interested in collaborative greening organizations like Learning Landscapes …

High-Resolution Geospatial Database: National Criteria-Air-Pollutant Concentrations In The Contiguous U.S., 2016–2020, Tianjun Lu, Sun-Young Kim, Julian D. Marshall

Epidemiology and Environmental Health Faculty Publications

Concentration estimates for ambient air pollution are used widely in fields such as environmental epidemiology, health impact assessment, urban planning, environmental equity and sustainability. This study builds on previous efforts by developing an updated high-resolution geospatial database of population-weighted annual-average concentrations for six criteria air pollutants (PM_2.5, PM₁₀, CO, NO₂, SO₂, O₃) across the contiguous U.S. during a five-year period (2016–2020). We developed Land Use Regression (LUR) models within a partial-least-squares–universal kriging framework by incorporating several land use, geospatial and satellite–based predictor variables. The LUR models were validated using conventional …

Zinc Or Swim: Investigating Zinc Pollution From Restoration Materials, Megan R. Jensik

Honors Undergraduate Theses

Zinc is an essential nutrient, but can be toxic at high concentrations, negatively affecting various biological functions. Gabions are galvanized metals coated in zinc that are used for many human purposes, including coastal restoration efforts attempting to avoid using plastic materials. However, gabions can degrade in marine environments, potentially leaching metal into the water and soil. There is a knowledge gap regarding the occurrence and impacts of zinc pollution in the areas where these gabions are deployed, including the Indian River Lagoon (IRL). To address this, sediment samples were collected from the IRL and analyzed for their physical and chemical …

Performance Evaluation Of Managed Switch Configurations For Secure And Efficient Plc-Based Industrial Automation Networks, Ahmed Salama

All Graduate Theses, Dissertations, and Other Capstone Projects

This thesis explores how managed switches can improve network performance and security in PLC-based industrial systems. Using simulations in GNS3 and Cisco Packet Tracer, and packet analysis via Wireshark, the study compares unmanaged and managed switch configurations. Redundancy protocols, particularly STP and RSTP, are evaluated under failure scenarios. Results show that RSTP offers faster recovery times, making it more suitable for time-sensitive environments. Additionally, managed switch features like VLANs, port security, and MAC filtering significantly reduce vulnerabilities and improve network segmentation. The findings highlight the importance of incorporating both cybersecurity and redundancy in industrial network design as systems move toward …

Teaching Cases: How Legal Writing Textbooks Approach The Rule Support Section, Alissa Bauer

Faculty Scholarship

No abstract provided.

Dynamical Mechanisms Of Neural Computation, Frederick Michael Berl

Yale Graduate School of Arts and Sciences Dissertations

The brain is one of the most complex dynamical systems in the universe and despite our everyday familiarity with it, the intricacies of how it functions remain a mystery to us. It is enormously powerful, continuously learning, and able to perform computations flexibly and adapt to novel situations. Although science presently has an understanding of how individual neurons work and a general idea of what the functions of each region in the brain are, how the computations of each neuron are modulated by context and how the various regions work together to produce behavior are unclear. Here, we explore the …

Adaptation Of Learning Dynamics And Feature Representations Via The Neural Kernel, Lianghui Peng

Yale Graduate School of Arts and Sciences Dissertations

The ability to learn from experience is essential for both biological and artificial agents. To learn efficiently in complex, high-dimensional environments, agents must generalize strategically from limited data by focusing on features relevant for the task. The generalization strategy, known as inductive bias, shapes the dynamics of learning. Previous works have established the theory of neural tangent kernels that describes the learning dynamics of artificial neural networks. However, a comparable framework for understanding and quantifying inductive bias in biological systems performing behavioral tasks remains underdeveloped. Here, we introduce a neural kernel framework to characterize inductive biases of humans and artificial …

Random Matrices And Statistical Inference With Correlated Structures, Haoyu Wang

Yale Graduate School of Arts and Sciences Dissertations

Random matrices play a central role in modern probability theory and high-dimensionalstatistics, both as fundamental mathematical objects and as powerful tools for inference. This dissertation presents several works on random matrix theory and its connections to statistical inference with correlated structures in high dimensions. On the random matrix side, we investigate the spectral properties of sample covariancematrices. Our approach is built upon the resolvent method, and we utilize local laws for various spectral analyses. Specifically, our contributions are three-fold: (1) we attain the first explicit rate of convergence for the largest eigenvalue of sample covariance matrices; (2) we derive the …

(1+1)D Topological Phases Enriched With Fusion Category Symmetries, Xinping Yang

Yale Graduate School of Arts and Sciences Dissertations

Symmetry and its anomaly constrain a system's dynamics and provide a universal characterization of its behaviors. It serves as a powerful tool to understand exotic phases of matter, especially symmetry-protected topological (SPT) orders. The notion of generalized symmetries requires extending our previous understanding of topological phases to those enriched by fusion category symmetries, yet new mathematical formalism is needed to apply unitary fusion category symmetries to a microscopic system. This thesis starts with a model-independent description of an abstract spin chain viewed as a net of C*-algebras. From a microscopic SymTFT, categorical structures describing symmetry and symmetry charges can be …

Bosonization And Fermionization Of Categorical Symmetries, Karan Bhatia

Yale Graduate School of Arts and Sciences Dissertations

The thesis investigates the processes of bosonization and fermionization within the framework of fusion category symmetries, which serve as the mathematical language for understanding topological phases of matter. We show that all fermionic fusion categories can be bosonized via a minimal braiding construction, providing a systematic method to relate fermionic and bosonic topological orders. Conversely, certain bosonic fusion categories that contain a Z_2 symmetry object can be fermionized using the same construction. However, a concrete obstruction arises when attempting to fermionize the remaining bosonic fusion categories, specifically those whose fusion rules involve two fixed points fusing into an odd number …

Two Paradigms Of Research And Their Influence On The Study Of Animal Behaviour, David Fraser

General - Animal Cognition and Behavior

Taxonomist Roy Crowson identified a fundamental difference among sciences. What he called “natural history” is exemplified by classical biology; it begins by observing, describing and classifying phenomena in the real world, then seeks patterns and concepts that help to synthesize and explain the observations, and proceeds to measurement and experimentation grounded in that framework. What he called “natural philosophy” is exemplified by classical physics; it postulates fundamental principles or concepts that are thought to apply universally, and the research proceeds more directly to measurement and experimentation directed at these principles or concepts. The study of animal behaviour has been influenced …

Description’S Displacements: Writing Experience In Musil, Benjamin, And Bachmann, Aida Feng

Yale Graduate School of Arts and Sciences Dissertations

This dissertation unfolds the ways in which description emerged as an active site for reconfiguring human experience in the writing experiments of the 20th century. Description, as a procedure for presenting and arranging the phenomena of reality, typically constructs an epistemological realm of experience that progresses toward comprehension and internal consistency. Understood in this way, description mediates one kind of experiential reality while foreclosing others. This project enlarges description’s operative capabilities toward a presentational mode that does not merely re-describe the phenomenal objects in this reality. To do so, it foregrounds writers and thinkers who conversed directly with philosophical traditions …

Cell State Dependent Strategies For Resolving Fundamental Properties Of Ligands Via Receptor Processes, Andrew Goetz

Yale Graduate School of Arts and Sciences Dissertations

Ligands may carry information through features such as their concentration, identity, and spatial distribution. Cells that can resolve these properties gain access to additional dimensions of information which may be beneficial as certain ligand properties possess unique features (e.g., ligand identity does not disperse with distance the way concentration does). Cells can accomplish this, at least in part, through the use of signaling cascades initiated by membrane receptors which bind to the ligand and activate downstream processes. The properties of these signaling cascades depend on the "state" of the cell (a property encompassing important cell features like protein levels and …

Development Of The Human Brain Networks During Infancy, Huili Sun

Yale Graduate School of Arts and Sciences Dissertations

In early infancy, the human brain undergoes rapid network construction and remodeling. Advances in neuroimaging have made non-invasive, in-vivo observation of these brain changes possible during the perinatal period. However, how the brain develops to support dynamic activity and cognitive function remains unclear. In this thesis, I leverage the network control theory to model brain controllability - the capacity to drive activity changes - and examine its role in neurodevelopment. I first outline the developmental trajectories of controllability during the perinatal period and link them to synaptogenesis with cross-species models. Next, I introduce a machine-learning framework to explore how white …

Causal Inference For Environmental And Text-Based Interventions, Megan Ayers

Yale Graduate School of Arts and Sciences Dissertations

Causal inference provides statistical tools for generating empirical evidence about causal relationships. In conventional settings, randomized experiments can enable estimation of causal effects with simple methods and under weak assumptions, but many pressing causal questions concern complex systems where standard approaches break down. This dissertation presents advances and insights for such cases, first in the context of carbon markets and conservation programs, and then in settings where text serves as treatment. In the first chapter, we develop a generalized causal inference framework for analyzing forest carbon protocols. Recent work has questioned the credibility of forest carbon offsets as an environmental …

Satellite Galaxy Kinematics: A Competitive And Complementary Probe Of The Galaxy-Halo Connection And Cosmology, Kaustav Mitra

Yale Graduate School of Arts and Sciences Dissertations

Most cosmological analyses of galaxy surveys under-utilize the data from the smallest scales. Firstly, analytical calculations become challenging in the fully non-linear regime. Moreover, the small scales are inherently plagued by several systematic uncertainties, such as the effects of baryons. Interestingly, analyses that have delved into the non-linear regimes of structure formation, mostly using galaxy clustering or weak gravitational lensing, often show an ongoing tension with the probes of early Universe physics, such as the cosmic microwave background, about the exact values of some of the cosmological parameters. This begs the following questions: (a) Can we think of a new …