Data Science Commons^™

Data-Driven Climate Damage Functions For Capital Formation: Estimating The Climate Penalty Using Maching Learning, Pramudya Wicaksono

All Graduate Theses, Dissertations, and Other Capstone Projects

Traditional integrated assessment models assume parametric climate damage functions that may miss nonlinearities, heterogeneity, and dynamic effects on investment. This thesis develops a data-driven climate damage function for capital formation by estimating the predictive relationship between climate conditions and future gross fixed capital formation (% GDP) across 125 countries over 1982–2019. We construct a panel dataset by combining daily ERA5 climate reanalysis data (accessed via the Copernicus Climate Data Store API and aggregated to yearly country-level variables including temperature anomalies, extreme heat days, frost days, precipitation, and solar radiation) with economic indicators from the World Bank World Development Indicators and …

An Ensemble Classifier For Ordinal Outcomes In High-Dimensional Genomics Data, Heranga K. Rathnasekara, Sinjini Sikdar

Mathematics & Statistics Faculty Publications

Analysis of genomics data for predicting disease outcomes is a fast-growing field in medical research. There often exist categorical, specifically, ordinal outcomes that need to be predicted based on genomic profiles. This has led to recent development of some high-dimensional ordinal classification methods that can address the large dimensionality of the genomic covariate set. These high-dimensional ordinal models tend to vary widely in their performance depending on the data they are applied to and the evaluation criteria used. In this article, we outline an ensemble ordinal classifier that integrates different ordinal modeling approaches through bootstrap-based model evaluation, multi-metric performance assessment, …

Neighborhood Embeddings And Scalable Learning For Optimal Transport And Unbalanced Optimal Transport, Muhammad S. Rana

Mathematics Dissertations - Archive

Dimensionality reduction techniques are developed from the assumption that high-dimensional data often arises from low-dimensional structures embedded into the high-dimensional ambient space. Classical dimensionality reduction methods rely on the Euclidean distance, which may fail to capture the geometric structures of the datasets. This dissertation includes alternative metrics for dimensionality reduction techniques and challenges in applying these techniques.

First, we investigate the Wasserstein distance based neighbor embeddings for dimensionality reduction methods and compare the classification and clustering performance with the classical Euclidean based methods. The Wasserstein distance models the data as probability distributions and compares two distributions applying optimal transport (OT) …

Volatility Modeling With An Application To Risk Parity Portfolios, Kenneth Hou

CMC Senior Theses

This thesis studies volatility modeling in the context of risk parity portfolio construction. I compare three risk parity portfolios that differ only in their underlying volatility model: a historical covariance baseline, a Bayesian stochastic volatility model, and a GRU–GARCH hybrid neural network. Using daily returns on Kenneth French’s five industry portfolios from January 2016 through December 2025, I construct monthly rebalanced portfolios under each model, with the SV and GRU forecasts embedded in hybrid covariance matrices that combine forecasted volatilities with rolling historical correlations. The results document a divergence between forecast accuracy and portfolio performance: the SV model is the …

Microbial Community Structure In Global Soils, Matthew Jabro

CMC Senior Theses

Soil harbors the most diverse microbial communities on Earth, yet whether predictable community types exist across biomes and whether taxonomic composition encodes habitat of origin remain open questions at global scale. This thesis addresses both questions by applying unsupervised clustering and supervised classification to transformed 16S ribosomal RNA (rRNA) amplicon profiles from two independent datasets: the global topsoil survey of Bahram et al. (193 samples) and the Earth Microbiome Project (EMP) soil subset of Thompson et al. (2,209 samples). Application of a sample clustering method based on a mixture of Gaussian Graphical Models (MixGGM) identified 19 clusters in the topsoil …

Analysis Of Δ¹¹B As A Seawater Ph Proxy: Comparing Ocean Circulation Inverse Model Output With Marine Calcifier Geochemistry, Jesse I. Dong

CMC Senior Theses

Increasing anthropogenic carbon flux into the oceans decreases seawater pH, alters dissolved inorganic carbon speciation, and reduces biogenic calcification. The marine calcifiers— specifically corals and coralline algae—incorporate elements from surrounding seawater into their carbonate structures, which preserve past records of ocean carbon chemistry. In particular, boron in biogenic carbonate is a potentially valuable proxy for historical ocean pH across human timescales. Within seawater, boron primarily exists as boric acid B(OH)3 and borate ions B(OH)4 - , where higher pH favors the formation of borate ions. Borate ions preferentially incorporate the heavier ¹¹B isotope over 10B. On the other hand, if …

Identifying New Programme Development Viability, Grant Goodwin

ICT

Higher Education Institutions (HEIs) face the challenge of developing programmes that respond to changing labour market needs while providing graduates with relevant employment opportunities and ensuring institutional financial viability. Rapid technological and economic changes make it increasingly important for HEIs to use reliable data to identify emerging skills and workforce demands. This project explores the use of machine learning and nationally collected employment data to support evidence-based decision-making in higher education programme development. By analysing patterns and relationships within labour market data, machine learning models can help identify areas of growing demand and provide insights into the potential alignment between …

Seasonal Dublin Airport Passenger Arrivals Forecast For The Economy Sector Of Dublin Airport, Roberto Tavares De Oliveira Neto

ICT

Dublin Airport plays a significant role in Ireland’s tourism and commercial sectors, with passenger demand directly influencing retail, hospitality, car rental and other airport-related businesses. Accurate forecasting of passenger numbers can support these sectors in planning marketing activities, managing stock levels and making evidence-based operational decisions. This project develops a monthly forecasting framework for passenger arrivals at Dublin Airport using data from the Central Statistics Office (CSO). Building on previous exploratory data analysis, the study evaluates five time series forecasting approaches: ARIMA, SARIMA, Holt-Winters Triple Exponential Smoothing, TBATS, and an automated model comparison pipeline using PyCaret. The models are assessed …

Machine Learning For Early Obesity Risk Prediction, Giuseppe Cutugno

ICT

Obesity is a major global public health concern, with significant implications for individual health, healthcare systems, and wider economic outcomes. Early identification of obesity risk can support preventive strategies and encourage healthier lifestyle choices before health conditions become more severe. This project develops a machine learning framework for estimating obesity levels using data relating to individuals’ physical characteristics, eating habits, lifestyle behaviours, and demographic factors. Following the CRISP-DM framework, the project examines the structure and limitations of the dataset, including its mixture of objective measurements, survey-based variables, and synthetically generated observations. Two modelling approaches are considered, one including BMI as …

Understanding Host Behaviour And Property Review Characteristics Using New York City Airbnb Dataset, Anna Szkwara

ICT

This project applies strategic thinking and the CRISP-DM methodology to analyse Airbnb listings in New York City and identify patterns associated with host performance and market vulnerability. Airbnb has become a major global accommodation platform, creating opportunities for individual hosts while also increasing competition within the short-term rental market. The project focuses on whether data-driven analysis can identify factors that may influence host success and provide useful insights for hosts with less experience or expertise than larger hospitality organisations. The dataset contains 85 variables, many of which require careful evaluation due to redundancy, high cardinality, sensitivity, or limited relevance to …

Predicting Product Returns In Online Retail, Mihaela Cristina Stefanache

ICT

Product returns are a significant challenge for online retailers, contributing to additional operational costs and affecting inventory management and profitability. This project develops and evaluates three machine learning models to predict product returns for a UK online retailer, building on the data understanding and preparation completed in the previous CA2 capstone project. Following the CRISP-DM framework, the study extends the analysis through enhanced exploratory data analysis, feature engineering, model development, hyperparameter optimisation, cross-validation, and model interpretability. Logistic Regression, a Tuned Random Forest, and XGBoost are evaluated, with the Tuned Random Forest achieving the strongest overall performance, obtaining an F1 score …

Predictive Maintenance For Manufacturing Equipment, Paloma De Andrade Batista

ICT

Unplanned equipment downtime is a significant challenge in manufacturing, resulting in substantial productivity losses and operational costs. Predictive maintenance, enabled by machine learning and big data analytics, offers an opportunity to identify potential equipment failures before they occur and improve maintenance efficiency. This report extends a previous capstone project that applied Random Forest and Logistic Regression to the AI4I 2020 Predictive Maintenance Dataset. The current study expands the analysis by incorporating XGBoost, systematic hyperparameter optimisation, cross-validation, and SHAP-based model interpretability. In addition, SWOT and PESTLE analyses, alongside a legal and ethical assessment, examine the broader strategic and responsible implementation of …

Predicting Loneliness Among Older Adults In Ireland Using Supervised Machine Learning, Ariadne Chaves Miranda

ICT

Over the last two decades, technology has grown exponentially and has facilitated communication that helps individuals remain connected. However, this has also contributed to social isolation and lack of physical interaction. One consequence of this phenomenon is loneliness, which is understood as an unpleasant subjective state of discrepancy between the desired amount of companionship or emotional support and what is available in the person’s environment (Prohaska and Burholt, 2020). In the European context, Ireland has emerged as the loneliest country in Europe with 20% of its population that have reported feeling lonely most or all the time (Schnepf et al., …

Beyond The Lace Index: Benchmarking Machine Learning Architectures And Explaining 30-Day Hospital Readmission Risk With Shap Analysis, Carl E. Hughes Iii

Williams Honors College, Honors Research Projects

Unplanned 30-day hospital readmission remains a fundamental challenge in US healthcare, associated with increased risk to patient recovery and representing an estimated $52.4 billion in annual expenses (Beauvais et al., 2022). While the rigorously validated LACE index serves as the clinical standard for readmission modeling, its linear structure and four explanatory variables lack the complexity to capture the high-dimensional and interactive nature of patient risk. This study utilizes an admission granularity level cohort of the MIMIC-IV database to develop and compare machine learning architectures against the baseline LACE index. Due to the imbalanced prevalence of readmission, the penalized logistic regression, …

Modeling Housing Prices: Which Features Matter Most?, Alex Ruvolo

Williams Honors College, Honors Research Projects

This paper attempts to find the biggest factors and traits that influence the cost of housing. This will include the lot size, type of street, utilities, neighborhood, year built, heating, electrical, yard size, number of different rooms, age, condition, and others. I will attempt to answer the question of whether the prices of houses have changed within the last 5 to 10 years, and obviously this is an easy question to answer. However, the bigger question beyond this is are the main factors affecting housing prices all important in explaining this relationship? Is one factor more important than the rest …

Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari

Bioengineering Theses

This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …

Differences In Biologic Clinical Trials For Chronic Rhinosinusitis With Nasal Polyps—Are We Comparing Apples With Oranges?, Marjolein Cornet, Peter W. Hellings, Martin Desrosiers, Martin Wagenmann, Richard Follows, Laura Walrave, Luz Adriana Jimenez, Lee Tombs, Dawn Edwards, Peter Howarth, Joseph K. Han

Department of Otolaryngology (ENT) Faculty Publications

In recent years, several biologics targeting Type 2 inflammation have been developed for treating chronic rhinosinusitis with nasal polyps (CRSwNP). These have been studied in registrational randomized controlled trials (RCTs), which vary in their patient populations, trial design, endpoints, geography, timing, or data-handling processes. While (in)direct treatment comparisons and meta-analyses have been carried out to compare efficacy results from RCTs, often these fail to properly account for these between-study differences. Here, we summarize the key between-study differences that can influence trial outcomes and highlight the resulting challenges faced when comparing outcomes from different Phase III RCTs of biologics in CRSwNP.

Floodnet Methodology For Determining Flood Sensor Locations, Polly Pierone, Véronëque Ignace, Hannah Eisler Burnett, Hayley Elszasz, Brett F. Branco, Andrea Silverman

The Science and Resilience Institute at Jamaica Bay, SRIJB

FloodNet NYC is a collaboration between the City University of New York (CUNY), New York University (NYU) and NYC government agencies. In 2022, the NYC Department of Environmental Protection (NYC DEP) funded FloodNet NYC to install up to 500 flood sensors across New York City (NYC) by the end of June 2027. To meet this goal, FloodNet developed and continued to refine a flood sensor placement methodology to ensure the usefulness of sensor data for flood response, preparedness, mitigation, and overall resilience. Members of the FloodNet team from both technical and community-facing aspects of the project worked together to develop …

Deep Learning Approaches For Voltammetric Analysis Of Coffee, Ryan Koes

Honors Theses

This thesis investigates deep learning approaches for voltammetric analysis of brewed coffee using a low-cost electrochemical system and screen-printed electrodes (SPEs). Traditional analytical methods, such as high-performance liquid chromatography (HPLC) and gas chromatography-mass spectrometry (GC-MS), provide precise quantification of key compounds but require expensive instrumentation and specialized expertise, limiting accessibility. While SPEs offer a more accessible alternative, they yielded poor results with traditional processing; however, when combined with a neural network, the system proved more effective. In experiments with 132 coffee samples, mean errors for caffeine, CGA, and TDS predictions were 52.98 ppm, 70.48 ppm, and 0.08%, respectively. These findings …

Utilizing Computer Modeling To Optimize Electric Fields Within Xenon Time Projection Chambers, Miles Meloni

Honors Theses

XENONnT is a physics experiment designed with the goal of detecting dark matter particles. The detector is a time projection chamber; a series of charged electrodes creates an electric field, surrounding a central body filled with liquid and gaseous xenon. Photomultiplier tubes (PMTs), positioned on either end of the chamber, serve to detect light signals. We seek to minimize the root mean square of the electric field norms experienced by the PMTs. This quantity corresponds to the variance in the electric field observed by the PMTs. Establishing a consistent electric field is important to maintaining these sensitive components. The electric …