Digital Commons Network^™

Data-Driven Streamflow Forecasting In The Upper Colorado River Basin Using Spatio-Temporal Graph Networks, Akhila Akkala

All Graduate Theses and Dissertations, Fall 2023 to Present

Forecasting river flow is essential for managing water supplies, reducing flood risk, and supporting healthy ecosystems. In the Upper Colorado River Basin, much of the yearly water comes from melting snow. However, many traditional models struggle to capture how snowpack and river flow interact, especially across such a large and complex region.

This study uses a modern machine learning approach called a Spatio-Temporal Graph Neural Network (STGNN) to improve streamflow prediction. The model uses Snow Water Equivalent (SWE)—a measure of how much water is stored in the snowpack—along with river flow data. By treating each river gauge as part of …

Introduction To Machine Learning And Machine Learning Systems, Raffi T. Khatchadourian Ph.D.

Open Educational Resources

Lecture slides introducing machine learning and machine learning systems for an undergraduate software engineering course. Topics include what machine learning is and how it differs from traditional programming, foundation models, the major types of learning (supervised, unsupervised, reinforcement, and others), and applications across domains. Using a food-delivery time-prediction case study, the deck walks through a typical ML pipeline—data collection and cleaning, feature engineering, model training, and evaluation—and covers evaluation methods (precision and recall, confusion matrices, error measures) along with underfitting versus overfitting and the realities of learning and evaluation in production. Based on "Machine Learning in Production/AI Engineering" by Christian …

Advances In Artificial Intelligence For Glioblastoma Radiotherapy Planning And Treatment, Reid Master, Nesha Rubin, James Sampson, Kamlesh K Yadav, Shruti Pandita, Aria Sabbagh, Anika Krishnan, Patrick J Silva, Kenneth S Ramos, Vincent Gregoire, Nikos Paragios, Sunil Krishnan, Tej K Pandita

The Brown Foundation: Institute of Molecular Medicine

Glioblastoma is an aggressive central nervous system tumor characterized by diffuse infiltration. Despite substantial advances in oncology, survival outcomes have shown little improvement over the past three decades. Radiotherapy remains a cornerstone of treatment; however, it faces several challenges, including considerable inter-observer variability in clinical target volume delineation, dose constraints associated with adjacent organs at risk, and the persistently poor prognosis of affected patients. Recent advances in artificial intelligence, particularly deep learning, have shown promise in automating radiation therapy mapping to improve consistency, accuracy, and efficiency. This narrative review explores current auto segmentation frameworks, dose mapping, and biologically informed radiotherapy …

Fish-Spec: Fast Identification System For Handheld Spectroscopy And Species Classification, Mitchell Sueker, Nicholas Mackinnon, Gregory Bearman, Amanda Tabb, Diane Kim, Rosalee S. Hellberg, Alireza Akhbardeh, Hamid Reza Marateb, Jianwei Qin, Moon Kim, Fartash Vasefi, Hossein Kashani Zadeh

Food Science Faculty Articles and Research

Accurate fish species identification is critical to prevent mislabeling and fraud in the seafood industry. We present a handheld multi-mode point spectroscopy system that combines fluorescence (365 and 395 nm excitation) and reflectance measurements in the visible to near-infrared (∼350–900 nm) and short-wave infrared (∼900–1700 nm) regions for rapid, non-destructive classification of fish fillets. Tissue spectra were acquired at 25 positions on 68 fillets from 11 species, in both frozen and thawed states. Feature-level fusion across all four modes enabled higher classification accuracy than any single mode alone. A global machine-learning model classified all species with 85 ± 2.8 %, …

Archaeological Predictive Meta-Modeling In Pre-Columbian Mexico, Peter Stamm

Electronic Theses and Dissertations

Archaeological Predictive Modeling stands firmly as an important tool for Archaeologists to predict undiscovered sites from civilizations all across the globe. While powerful, this methodology is not without its own set of qualms. Striking a balance between pure a data-driven approach while also observing leading expert theories can be a complicated task. Going further, deciding on the specific domain of features to emphasize or overlook can be a challenge within itself, as one misstep can drastically change the output of model, sometimes for the worst. In addition, creating models that can expose their reasoning process can be rather difficult to …

Navigating Structure, Function, And Stability: Bridging Immunotherapy And Protein Engineering In The Era Of Machine Learning, Christopher J. Haynie

Theses and Dissertations

The immune system is a remarkably adaptive network, yet it often fails to function optimally due to evasion strategies of pathogens or mutated cells. Many of these evasion strategies involve alterations in protein expression and function. Protein design is an area of computational biology with potential applications in improving protein function and therapeutic protein engineering. This thesis explores methods to enhance immune function and protein design across multiple scales, from molecular engineering of antibody fragments and chimeric antigen receptors (CARs) to cellular immune responses, and computational approaches for protein structure optimization. We characterize Thymidine Kinase 1-specific single-chain antibodies, highlighting both …

Machine Learning Model For Detecting Masked Hypertension In Young Adults, Brendyn Miller, Samuel Coeyman, Annemarie Wentzel, Carina M.C. Mels, William J. Richardson

Chemical Engineering Faculty Publications and Presentations

Introduction Cardiovascular disease (CVD) remains the leading global cause of mortality, with hypertension (HT) being a significant contributor, responsible for 56% of CVD-related deaths. Masked hypertension (MHT), a condition where patients exhibit normotensive blood pressure (BP) in clinical settings but elevated BP in out-of-clinic measurements, poses an elevated risk for cardiovascular complications and often goes undiagnosed. Current diagnostic methods, such as ambulatory BP monitoring (ABPM) and home BP monitoring (HBPM), have limitations in feasibility and accessibility. Methods This study aimed to address these challenges by leveraging machine learning (ML) models to predict MHT based on clinical data from a single …

A Novel Hybrid Intrusion Detection Model: A New Metaheuristic Approach For Feature Selection Based On Ai Techniques For Cyber Threat Detection, Maryam Mahdi Alhusseini, Alireza Rouhi

Iraqi Journal for Computer Science and Mathematics

The rapid increase in internet usage, digital transformation, and the rise of interconnected devices have greatly expanded the attack surface, introducing new and evolving cybersecurity challenges. Conventional security solutions frequently have difficulty adjusting to complex threats and the vast dimensionality of network traffic data, particularly in the case of imbalanced datasets. To tackle these challenges, this research introduces a Hybrid Intrusion Detection System (HyIDS-EVO) that combines the Energy Valley Optimizer (EVO) for feature selection and dimensionality reduction with machine learning classifiers, which include Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbors (KNN). The system’s effectiveness …

Using Machine Learning To Predict Maintenance Intentions Of Septic System Owners, Audrey Mccrary, Luna Yang, Allen Berthold

Journal of Contemporary Water Research and Education

The scope of literature related to septic system maintenance from an educational and behavioral perspective, rather than a quantitative water quality approach, is limited. The water resources management community needs improved insight into the human factors related to septic system maintenance decisions and identification of effective intervention strategies. Using a modified Theory of Planned Behavior (TPB; Ajzen 1991) framework, the purpose of this study was to identify factors that predict homeowners’ intention to have their systems inspected and pumped within the next three years. As part of a small-scale educational program, a survey was sent to 1,374 homeowners with septic …

Developing A High-Throughput Machine Learning Screening Platform For Genetic And Pharmacological Modulators On Caenorhabditis Elegans Seizure Behavior, Paul A. Scarpinato

Electronic Theses and Dissertations 2020 - Present

Epilepsy is a chronic neurological disorder characterized by recurrent seizures that affect over 50 million people worldwide, including more than 3.5 million in the United States. Seizures arise from a disrupted balance between excitation and inhibition. Although antiepileptic drugs (AEDs) remain the primary treatment to restore the excitation and inhibition balance, approximately 30% of patients experience drug-resistant epilepsy, highlighting the need for additional antiseizure medications. The Caenorhabditis elegans electroshock assay was developed in relative alignment with the rodent maximal electroshock seizure (MES) test, the gold standard for preclinical AED screening, provides a cost-effective platform for prescreening candidate AEDs.

This work …

Multiplexed Integrin Detection And Cancer Cell Classification Using Multicolor Gap-Enhanced Gold Nanorods And Machine Learning Algorithm, Suprava Shah, Reed Youngerman, Alberto Luis Rodriguez-Nieves, Mitchell Lee Taylor, William Rodney Bantom, David Thompson, Jingyi Chen, Yongmei Wang, Xiaohua Huang

Chemistry & Biochemistry Faculty Publications and Presentations

Integrins, cell-surface adhesion receptors involved in tumor progression, invasion, and metastasis, serve as crucial biomarkers for cancer diagnosis and therapeutic targeting. Multiplexed detection of integrins and cancer cell classification at the single-cell level allows for comprehensive profiling, facilitating precise identification and categorization of tumor cells that are heterogeneous in integrin expression and cell subtype. In this study, we developed a five-plex detection platform and demonstrated integrin profile for cancer cell classification leveraging surface-enhanced Raman scattering (SERS) with gap-enhanced gold nanorods (GENRs) in conjunction with advanced computational analysis. Specifically, we synthesized GENRs bearing five distinct Raman nanotags, each producing a unique …

Advancing Road Safety Through Data Integration, Location Accuracy, And Risk-Based Route Optimization, Lars Skaug

Electronic Theses and Dissertations 2020 - Present

This dissertation advances transportation safety through three interconnected contributions that address fundamental challenges in crash data analysis and application. First, we present a comprehensive survey of road crash analysis methodologies, tracing the evolution from traditional statistical approaches to modern machine learning techniques while identifying critical gaps between research sophistication and practical implementation. This survey reveals that while methodological advances have been substantial, ongoing data quality issues, particularly in location accuracy and completeness, limit the effectiveness of even the most sophisticated analytical approaches.

Building on these findings, we develop a novel system to validate and correct crash location data using multi-modal …

A Multiomics Recovery Factor Predicts Long Covid In The Impacc Study, Gisela Gabernet, Jessica Maciuch, Jeremy P Gygi, John F Moore, Annmarie Hoch, Caitlin Syphurs, Tianyi Chu, Naresh Doni Jayavelu, David B Corry, Farrah Kheradmand, Lindsey R Baden, Rafick-Pierre Sekaly, Grace A Mccomsey, Elias K Haddad, Charles B Cairns, Nadine Rouphael, Ana Fernandez-Sesma, Viviana Simon, Jordan P Metcalf, Nelson I Agudelo Higuita, Catherine L Hough, William B Messer, Mark M Davis, Kari C Nadeau, Bali Pulendran, Monica Kraft, Chris Bime, Elaine F Reed, Joanna Schaenman, David J Erle, Carolyn S Calfee, Mark A Atkinson, Scott C Brakenridge, Esther Melamed, Albert C Shaw, David A Hafler, Alison D Augustine, Patrice M Becker, Al Ozonoff, Steven E Bosinger, Walter Eckalbar, Holden T Maecker, Seunghee Kim-Schulze, Hanno Steen, Florian Krammer, Kerstin Westendorf, Bjoern Peters, Slim Fourati, Matthew C Altman, Ofer Levy, Kinga K Smolen, Ruth R Montgomery, Joann Diray-Arce, Steven H Kleinstein, Leying Guan, Lauren Ir Ehrlich

Faculty, Staff and Students Publications

Background: Following SARS-CoV-2 infection, approximately 10%–35% of patients with COVID-19 experience long COVID (LC), in which debilitating symptoms persist for at least 3 months. Elucidating the biologic underpinnings of LC could identify therapeutic opportunities.

Methods: We utilized machine learning methods on biologic analytes provided over 12 months after hospital discharge from more than 500 patients with COVID-19 in the IMPACC cohort to identify a multiomics “recovery factor,” trained on patient-reported physical function survey scores. Immune profiling data included PBMC transcriptomics, serum O-link and plasma proteomics, plasma metabolomics, and blood mass cytometry by time of flight (CyTOF) protein levels. Recovery factor …

Towards Automated And Explainable Insider Threat Response In Electronic Health Records: A Role-Aware Machine Learning Framework, Luca Lippi Ornstil

Master's Theses

Healthcare remains a prime target for cyberattacks, with insider misuse and credential compromise posing major risks to Electronic Health Records (EHRs). This thesis introduces a role-aware, explainable anomaly detection and response framework integrated with OpenEMR to address post-authentication threats. Four models—Local Outlier Factor (LOF), Isolation Forest, Autoencoder, and Graph Neural Network (GNN)—detect behavioral deviations across temporal, device, and role-based features, with LOF serving as the primary runtime detector. A configurable policy engine maps anomaly severity to proportional actions, from email alerts to read-only restrictions or account suspension, all reversible and auditable. Evaluation on real EHR logs shows the system’s operational …

Image Captioning Through The Lens Of The Gricean Maxims: Generating Meaningful And Relevant Image Descriptions, Annika Lindh

Doctoral

Image captioning models enable us to automatically generate natural language image descriptions for previously unseen images. It combines the two fields of computer vision and natural language generation, allowing models to interpret the con tent of an image and communicate that knowledge through natural language text.

Research into image captioning has the potential benefit of reducing the gap in digital information availability between fully sighted individuals and those who are visually impaired. However, automatically generated captions often fail to provide the required level of detail and specificity to achieve this goal. Furthermore, current standard evaluation methods are insufficient at measuring …

Face Recognition Using Optimized Multi-Task Cascaded Cnn In Artificial Intelligence Systems, Sami Abduljabbar Rashid, Mustafa Maad Hamdi, Salah Ayad Jassim, Lukman Audah, Baraa Saad Abdulhakeem, Mohammed Salah Abood, Ahmed Adil Nafea

Baghdad Science Journal

Improving the accuracy level of face recognition system is still an open research area where it consists of certain limitations to attain maximum accuracy. In earlier days, several algorithms are developed using machine learning and deep learning models, but still, they need improvement in terms of accuracy. For that purpose, in this article a novel CNN model called the optimized multi cascaded CNN (OPT-MTC-CNN) in the artificial intelligence system is developed, which helps to overcome the accuracy issues in face recognition system. The algorithms that are incorporated in this model are Fully Convolutional Network (FCN), Convolutional Neural Network (CNN), and …

A Deep Learning Approach: The Impact Of Sentiment Analysis Of Bangladeshi Workers Over The World, Md Raihanul Islam Tomal, Tanveer Kader, Kohbalan Moorthy, Mazlina Abdul Majid

Baghdad Science Journal

In today's globalized world, the pursuit of better opportunities has led to a significant increase in immigration and foreign labor. This trend is particularly evident in Bangladesh, where many workers migrate annually to destinations such as Malaysia, Qatar, Saudi Arabia, and the UAE. Understanding the sentiments and emotions of these workers is crucial to preventing crimes, suicides, political unrest, and other security issues in host countries. As maximum workers usually come from rural Bangladeshi communicate they use local dialect for conversations and very popular widely used local dialect known as Pabnaia. This study did not identify any prior research specifically …

Dramatic Biases In Terrestrial Nitrogen Fixation In Earth System Models Revealed By Natural Isotope Signatures, Maoyuan Fang, Shushi Peng, Philippe Ciais, Daniel S. Goll, Benjamin Z. Houlton, Ying-Ping Wang, Yilong Wang, Pan Liu, Joshua B. Fisher, Pierre Regnier

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Biological nitrogen fixation (BNF) is the primary input of new reactive nitrogen to natural terrestrial ecosystems. However, this flux is poorly constrained due to its unclear drivers and associated control mechanisms. Here, we extend the existing theory of nitrogen (N) isotope mass balance to estimate BNF rates and then use a Bayesian approach to constrain the BNF rates in natural terrestrial ecosystems by using measurements of natural N-isotope ratios (δ¹⁵N) in plants (δ_P) and soil (δ_S). Together with pairwise δ_P and δ_S measurements from 18 forest sites covering diverse climates and thousands …

Green Carbon Dots In The Era Of Ai: Sustainable Synthesis, Intelligent Drug Delivery, Advanced Diagnostics, And Bioimaging, Emi̇ne Sezer, Fulden Ulucan Karnak, Si̇nan Akgöl

Turkish Journal of Biology

Background/aim: Green carbon dots (GCDs) are a rapidly developing class of nanomaterials that are revolutionizing various scientific disciplines due to their unique optical properties, low toxicity, and sustainable synthesis. This review offers a comprehensive roadmap for the field, emphasizing the synergy between GCDs and artificial intelligence (AI).

Materials and methods: We begin by detailing the sustainable synthesis of GCDs, highlighting green chemistry principles and the transformative role of AI in optimizing their production. Subsequently, we explore the critical characterization of GCDs, including their structural, optical, and biocompatibility assessment. The core of this study explores the diverse biomedical applications of GCDs, …

A Systematic Review Of Machine Learning In Heart Disease Prediction, Tathagat Banerjee, İshak Paçal

Turkish Journal of Biology

Background/aim: Cardiovascular diseases (CVDs) are a leading cause of global mortality, prompting the need for advanced predictive tools. While machine learning (ML) offers a powerful solution, there are significant challenges to clinical translation. This systematic review synthesizes the current state of ML in heart disease prediction, evaluating algorithmic performance, data utilization, and key translational challenges.

Materials and methods: Following PRISMA guidelines, a systematic search of literature published up to 2025 was conducted. From an initial pool of over 2500 records, a rigorous screening process yielded 65 studies for in-depth qualitative synthesis.

Results: Analysis showed that ensemble learning models dominate prediction …

Visible Image-Based Machine Learning For Identifying Abiotic Stress In Sugar Beet Crops, Seyed Reza Haddadi, Masoumeh Hashemi, Richard C. Peralta, Masoud Soltani

Plants, Soils and Climate Student Research

Previous researches have proved that the synchronized use of inexpensive RGB images, image processing, and machine learning (ML) can accurately identify crop stress. Four Machine Learning Image Modules (MLIMs) were developed to enable the rapid and cost-effective identification of sugar beet stresses caused by water and/or nitrogen deficiencies. RGB images representing stressed and non-stressed crops were used in the analysis. To improve robustness, data augmentation was applied, generating six variations on each image and expanding the dataset from 150 to 900 images for training and testing. Each MLIM was trained and tested using 54 combinations derived from nine canopy and …

A Machine Learning Framework For Classifying Lipids In Untargeted Metabolomics Using Mass-To-Charge Ratios And Retention Times., Christelle Colin-Leitzinger, Yonatan Ayalew Mekonnen, Isis Narvaez-Bandera, Vanessa Y. Rubio, Dalia Ercan, Eric A. Welsh, Lancia N F Darville, Min Liu, Hayley D. Ackerman, Julian Avila-Pacheco, Clary B. Clish, Kevin Hicks, John M. Koomen, Nancy Gillis, Brooke L. Fridley, Elsa R. Flores, Oana A. Zeleznik, Paul A. Stewart

Manuscripts, Articles, Book Chapters and Other Papers

INTRODUCTION: The identification of unknown metabolites remains a major challenge in untargeted metabolomics using liquid chromatography-mass spectrometry (LC-MS). This process typically depends on comparing mass spectral or chromatographic data to reference databases or deciphering complex fragmentation in tandem mass spectra. While current machine learning methods can predict metabolite structures using MS/MS (MS2) data, no approaches, to our knowledge, use only mass-to-charge ratio (m/z) and retention time (RT) from LC-MS data.

OBJECTIVE: To explore the potential of using the mass-to-charge ratio (m/z) and retention time (RT) from LC-MS data as standalone predictors for metabolite classification and propose a modeling framework which …

User Behaviour Prediction In E-Commerce Using Logistic Regression, Wei-Wen Lee, Noramiza Hashim, Shaymaa Al-Juboori

School of Engineering, Computing and Mathematics

From a psychological perspective, human behaviourreflectsunderlyingthoughtsand decision-making patterns, for example, consumer behaviour may correlate with the purchase decisions. In the fast-evolving e-commerce industry, predicting user behaviouris essential for enhancing marketing strategies, improving customer experiences, and increasing sales. However, traditional heuristic (e.g.market basket analysis) approaches to analysebuyer behaviour are often rigid and fail to adapt to complex consumer interactions. This research work develops a predictive model that analysesuser behaviour based on data such as historical purchasing patterns and demographic attributes. Based on a review of previous studies, Logistic Regression (LR) is utilized as theprimarymachine learning algorithm to estimate the likelihood of …

Toward Durable 3d Printed Structures, David A. Lange, Chenyue Shen

International Conference on Durability of Concrete Structures

Durability of 3-D printable concrete begins with control of flow and consolidation of the fresh material. 3D printed concrete needs to be fluid-like for pumping and extrusion but solid-like during placement to support the printed structure. High quality 3D printed materials must have excellent consolidation and a low volume of trapped voids. In practice, achieving this balance is challenging. This research addresses these challenges by leveraging machine learning and numerical simulation to model the fresh behavior of cement-based materials for 3-D printing. It begins with rheological characterisation to understand how mixture design factors influence rheological properties, laying the foundation for …

Integration Of Uav And Remote Sensing Data For Early Diagnosis And Severity Mapping Of Diseases In Maize Crop Through Deep Learning And Reinforcement Learning, Jerry Gao, Krinal Gujarati, Meghana Hegde, Padmini Arra, Sejal Gupta, Neeraja Buch

Faculty Research, Scholarly, and Creative Activity

Highlights: What are the main findings? A framework combining UAV, satellite, and weather data to detect crop diseases. Ensemble deep learning and reinforcement learning improve classification and severity mapping. What is the implication of the main finding? Enables near real-time, scalable crop disease management to reduce yield losses. Early detection and hotspot mapping optimize water and pesticide use for sustainability. Accurate and timely prediction of diseases in water-intensive crops is critical for sustainable agriculture and food security. AI-based crop disease management tools are essential for an optimized approach, as they offer significant potential for enhancing yield and sustainability. This study …

Improved Streamflow Forecasting Through Swe-Augmented Spatio-Temporal Graph Neural Networks, Akhila Akkala, Soukaina Filali Boubrahimi, Shah Muhammad Hamdi, Pouya Hosseinzadeh, Ayman Nassar

Computer Science Student Research

Streamflow forecasting in snowmelt-dominated basins is essential for water resource planning, flood mitigation, and ecological sustainability. This study presents a comparative evaluation of statistical, machine learning (Random Forest), and deep learning models (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Spatio-Temporal Graph Neural Network (STGNN)) using 30 years of data from 20 monitoring stations across the Upper Colorado River Basin (UCRB). We assess the impact of integrating meteorological variables—particularly, the Snow Water Equivalent (SWE)—and spatial dependencies on predictive performance. Among all models, the Spatio-Temporal Graph Neural Network (STGNN) achieved the highest accuracy, with a Nash–Sutcliffe Efficiency (NSE) of 0.84 …

Foundations Of Artificial Intelligence In Healthcare Diagnostics: A Systematic Survey, Raghad Tariq Al-Hassani

Al-Esraa University College Journal for Engineering Sciences

Artificial Intelligence (AI) is becoming the cornerstone of the future of healthcare diagnostics, that has to ability to change the healthcare diagnostic landscape in terms of diagnostic accuracy, speed, and availability. This systematic review investigates the basic methods, tools, applications, and challenges involved in the integration of AI in diagnostic medicine. It emphasizes the using of machine learning models, deep learning networks (e.g., CNNs), NLP for clinical documentation, and smart computing infrastructures, such as edge device and IoMT. They are making possible real-time, data-driven decision making that is already at human-expert-level performance or, in some cases, even better (in the …

Towards Autonomous Energy Management: Machine Learning For Effective Auditing And Optimization, Sameh O. Abdellatif, Sherif Ashraf, Mira Mohsen

Electrical Engineering

This study presents a fully automated procedure for energy management and auditing, applicable to a diverse range of residential and commercial loads, leveraging machine learning techniques across three key phases: load classification, benchmarking, and smart monitoring. The model effectively categorizes energy loads based on consumption patterns, establishes performance benchmarks through historical data analysis, and employs real-time monitoring to identify inefficiencies and predict future energy usage. Evaluating the model through four distinct case studies demonstrates its capability to optimize energy consumption in a techno-economic manner, achieving significant energy savings of 34.73 MWh/year for essential loads in Egypt, 215.67 MWh/year for HVAC …

Theoretical Investigation And Practical Validation Of Ai Based Fault Detection In Bjt Amplifier Circuits, Sameh O. Abdellatif, Kyrillos Selim, Ahmad Alaa, Ola Hassan

Electrical Engineering

Analog circuits are essential to electronic systems due to their variety of critical functions. Catastrophic faults, such as short- and open-circuit faults, can stop the circuit from functioning. Meanwhile, parametric faults such as drift due to temperature fluctuations, noise in components, and power supply issues cause the circuit to operate beyond its range. Such faults can harm the circuit and its constituent parts. Therefore, it is crucial to identify and address the issues brought on by these faults. Common traditional fault diagnosis methods that rely on manual testing and visual assessment are lacking in complex electronic systems and faults. Such …

Leveraging Machine Learning And Causal Inference For Loan Default Prediction, Luca Guida

Doctoral Dissertations and Master's Theses

This research explores a systematic application of machine learning techniques combined with causal inference to predict loan defaults in peer-to-peer lending. Accurately forecasting loan defaults is crucial for mitigating financial risk and optimizing lending strategies. This analysis is based on multiple datasets of loan applications spanning over a decade, containing detailed financial and credit information about borrowers. Beginning with extensive Exploratory Data Analysis (EDA) coupled with scaling strategies, the research identifies key trends in loan performance across a large number of factors, such as interest rates or borrower creditworthiness, and one objective is to determine from the many available predictors …