Data Science Commons^™

Predicting Repeat Purchases In E-Commerce Using Interpretable Machine Learning, Zahid Bhatti

ICT

This project investigates the prediction of repeat purchase behaviour in e-commerce using machine learning, with a focus on balancing predictive accuracy and interpretability. Large volumes of transactional and behavioural data are analysed to identify customer-level features that drive loyalty and repeat purchases. Various supervised learning models, including Random Forests and Logistic Regression, are evaluated for predictive performance, while SHAP (SHapley Additive Explanations) is employed to provide both global and local interpretability. The study aims to generate actionable insights for customer relationship management and marketing strategy, demonstrating how advanced predictive models can support informed business decisions without sacrificing transparency.

Predicting Customer Churn And Enhancing Retention Strategies Through Machine Learning., Swan Saung Lwin

ICT

Customer Churn is a critical challenge faced by businesses across industries, especially in the digital market. Many companies struggle to predict customer churn accurately and have difficulties in carrying out effective retention strategies. Key challenges include ineffective traditional methods, lack of insights into impact of different services, generalized retention strategies, and the need to have cost-effective retention strategies. This project aims to predict customer churn using machine learning and identify the impact of key services offered by a telecommunication company.

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 …

Predicting Customer Churn Using Machine Learning: A Data-Driven Approach, Alessandro Mendes Martins

ICT

This project focuses on predicting customer churn in the telecommunications sector using machine learning. A public dataset was analysed through exploratory data analysis, data cleaning, feature encoding, and scaling to prepare it for modelling. A Logistic Regression model was trained and optimised to identify customers likely to leave the service, achieving a ROC-AUC score of 0.861, with 79% accuracy, 82.3% recall, 51.9% precision, and an F1-score of 0.637. The analysis highlighted key factors influencing churn, including fibre-optic internet, month-to-month contracts, and electronic cheque payments, while longer tenure, two-year contracts, and usage of support services correlated with retention. These insights can …

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.

Customer Response To Marketing Campaigns., Alexandru Enoiu

ICT

This project applies machine learning to predict customer responses to marketing campaigns, aiming to enhance customer engagement and optimise resource allocation. Using a dataset containing demographic, lifestyle, and purchase behaviour data, a Random Forest classifier was developed to identify potential responders to marketing initiatives. The project follows a structured methodology including data exploration, preprocessing, model building, and evaluation. By accurately predicting customer behaviour, businesses can improve campaign targeting, design personalised marketing strategies, and allocate resources more efficiently. The results provide actionable insights to support customer segmentation and strategic decision-making, promoting business growth and customer satisfaction.

Credit Card Fraud Detection., Sonia Ndonga

ICT

This capstone project applies machine learning to detect credit card fraud, addressing a critical financial threat to banks and payment providers. Using an anonymised dataset of 284,807 transactions, which is highly imbalanced with only 0.172% fraudulent cases, three models—Logistic Regression, Random Forest, and Gradient Boosting—were developed and evaluated. The pipeline incorporates data preprocessing, feature engineering, hyperparameter tuning, cross-validation, and interpretability analysis using SHAP values, SHAPASH, and permutation importance. Random Forest achieved the highest performance with an ROC AUC of 0.97 and Average Precision of 0.66. The study also considers fairness, threshold optimisation, and practical deployment strategies, providing a robust automated …

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 …

Analysis Of Customer Churn In The Banking Sector And Its Mitigating Factors., Fiachra O Callaghan

ICT

This project investigates customer churn within the banking sector, analysing a dataset of 10,000 customers to identify patterns and potential drivers of attrition. By leveraging data analytics and visualization techniques, we aim to understand the demographic and behavioural factors influencing customer decisions to leave for competing banks. The study applies the CRISP-DM framework to structure the analysis, enabling iterative refinement of objectives and hypotheses as insights emerge. Findings indicate that certain customer segments, such as those aged 40–60, are more prone to churn, highlighting opportunities for targeted retention strategies, including fee reductions and tailored loyalty programmes. By integrating academic research …

A Comparative Analysis Of The Performance Of Customised And Pre-Trained Convolutional Neural Networks In The Classification Of Facial Expressions., Guilherme Soares Da Costa

ICT

Facial expression recognition (FER) is a highly relevant problem in the field of computer vision, with applications in various areas. Although this topic has made significant progress in recent years with deep learning, facial expression recognition continues to face significant challenges when faced with a noisy, imbalanced database, and low-resolution images, as is the case with the widely used FER2013 database. This work investigates the usability of different approaches based on Convolutional Neural Networks (CNNs) for the task of facial expression classification.

First, a custom CNN was developed and trained from scratch, using FER2013 as database. Subsequently, three well-known pre-trained …

Chess Evaluation And Player Profiling Using Convolutional Neural Networks (Cnns) And Spatial Recognition., Joel D’Mello

ICT

This thesis explores the feasibility of employing data analytics techniques in chess, with the purpose of profiling player styles and building a comprehensive chess analytics platform. The data set consists of over 20,000 anonymized games, and therefore, the study involved feature engineering, classification and visual analytics, in order to gain more insight into player decision making in chess. The data pre-processing part of analysis involved parsing Portable Game Notation (PGN) files, and feature engineering positional characteristics - material imbalance, pawn structure, king safety, and piece mobility - along with quantifying the sample using Average Centipawn Loss (ACPL) using Stockfish. ACPL …

Credit Card Default Prediction Using Machine Learning., Yassine Zohair

ICT

This project investigates the use of machine learning to predict credit card payment defaults, aiming to help banks and credit card companies mitigate financial losses. Using historical customer data, including demographics, income, education, and previous payment behaviour, three machine learning algorithms were implemented to forecast the likelihood of default. Techniques such as cross-validation, hyperparameter tuning, and SHAPASH were applied to improve model performance and interpretability. Accurate prediction of potential defaulters enables financial institutions to take proactive measures, such as adjusting credit limits or providing targeted financial guidance, thereby enhancing risk management and customer retention.

Automated Classification Of Cardiac Anomalies Through The Analysis Of Electrocardiogram Signals Using Convolutional Neural Networks., Yhosely Isset Villegas Baldiviezo

ICT

Electrocardiography (ECG) is a widely used non-invasive method for monitoring cardiac activity and detecting heart abnormalities. However, manual interpretation can be time-consuming and prone to human error, particularly for non-specialists. This study investigates the use of deep learning techniques, specifically convolutional neural networks (CNNs), to automate ECG signal classification using a large-scale dataset. A classical machine learning model is also included as a baseline for comparison. The aim is to evaluate the potential of deep learning as a clinical decision-support tool that can assist healthcare professionals in improving diagnostic accuracy and supporting early detection of cardiac conditions.

An Enhanced Deep Learning Framework For Crop Disease Detection Using Gan-Based Data Augmentation., Andrew Mc Guinn

ICT

Plant disease detection is a critical challenge in agriculture, where limited annotated datasets often hinder the training of robust deep learning models. This thesis explores the application of generative adversarial networks for data augmentation in the classification of six classes of sorghum diseases, addressing the scarcity of real training data. A lightweight convolutional neural network  (CNN) was employed as the classifier, trained under three experimental conditions: using only real images, a stratified mix of real and DCGAN-generated samples, and a stratified mix of real and WGAN-GP-generated samples.

The baseline CNN, trained on 279 real images, achieved an accuracy of 89.7%, …

Analysis Of The Patterns And Features Importance In Predicting Demand For Sustainable Urban Mobility. A Comparative Analysis Of Machine Learning Models Using The Dublin Bikes Dataset., Wojciech Sochanski

ICT

This study explores the application of machine learning models to predict demand in the Dublin bike-sharing scheme. A comprehensive literature review examines prior work on sustainable urban mobility, the evolution of bike-sharing schemes, the application of machine learning in predictive analytics and relevant case studies. Secondary data were gathered from publicly available sources, pre-processed and merged into a single, unified dataset. Exploratory data analysis was conducted before preparing the data for modelling to assess the data quality, with a focus on missing values.

Four predictive machine learning models – Linear Regression (LR), Decision Tree (CART), Random Forest (RF) and Gradient …

Clustering And Predictive Modelling Of Cryptocurrencies: An Empirical Study Of Lead–Lag Dynamics And Forecasting Performance., Viktor Varga

ICT

Cryptocurrency markets pose analytical challenges due to their volatility, non-stationarity, and complex interdependencies. Traditional econometric models have struggled with these features, while machine learning models often face overfitting and limited interpretability. This thesis has developed an integrated framework combining clustering, lead–lag detection, and predictive modelling to examine whether structural and temporal dependencies in cryptocurrency markets can improve forecasting performance.

Hourly OHLCV data for a selection of liquid cryptocurrencies from the Binance API over a thirteen-month period has been analysed. Dynamic Time Warping (DTW) has been used to identify asset clusters, while cross-correlation, Granger causality, and Vector Autoregression (VAR) have been …

Comparing Custom And Transfer-Learning Cnn Models For Chest X-Ray Classification: Evaluating Performance And Scalability With Kubernetes Orchestration., Christopher Anich

ICT

Chest radiography (CXR) is the primary imaging tool for respiratory diseases, but interpretation can be time-consuming and requires expertise. This study compares a small custom CNN (Victorio) with three transfer-learning models (MobileNetV2, EfficientNet-B0, ResNet-50) for three-class CXR classification (normal, pneumonia, tuberculosis) and evaluates deployment on a Kubernetes cluster. Using a balanced dataset of ~13,500 CXRs, models were trained with ImageNet pre-training and from scratch. Transfer-learning models achieved near-perfect accuracy (99–100%) and AUROC, while the custom CNN reached 87–91%. Explainability analyses confirmed models focused on relevant pulmonary regions. Kubernetes deployment showed low latency, with most delays due to service overhead rather …

Comparison Of Convolutional Neural Network Architectures For The Classification Of Microscopic Images: Performance Evaluation Of Lightweight Models., Cristian Ricardo Gonzalez Donoso

ICT

This study evaluates lightweight convolutional neural networks (CNNs) for multi-class classification of microscopic fungi images in CPU-only environments, addressing resource-limited laboratories and educational settings. Four pre-trained models—EfficientNetV2-B0, MobileNetV3-Small, MobileNetV2, and NASNetMobile—were compared on the DeFungi dataset (9,114 images, five fungal classes) using stratified training, realistic data augmentation, and two-stage transfer learning. Performance was measured via accuracy, macro-F1, precision, recall, and efficiency metrics including training time, inference latency, model size, and FLOPs. EfficientNetV2-B0 achieved the highest accuracy, while MobileNetV3-Small provided the best macro-F1 and lowest computational cost, making it the optimal choice for CPU-only deployment. Findings highlight the trade-off between predictive …

Comparison Of Statistical, Machine Learning, And Deep Learning Models For Time-Series Forecasting Using Weather Data From Dublin, Ireland., Erick Eduardo Rios Treviño

ICT

This study compares three time-series forecasting paradigms—statistical, machine learning, and deep learning—using ten-years of historical weather data from Dublin. The objective is to evaluate the performance of Prophet, XGBoost, and LSTM when forecasting daily solar radiation under multiple preprocessing strategies. An extensive data analysis was conducted, including descriptive statistics, inferential testing, stationarity assessment, outlier detection, feature selection, and exploratory visualisation. These steps revealed strong annual seasonality, nonlinear feature relationships, and variability across meteorological variables, informing the modelling framework and feature-engineering decisions. Four experiments were conducted using cleaned data, differenced data, log-transformed data, and cross-validation. Results show that XGBoost achieved the …

Demand Forecasting And Inventory Optimization In Mid-Sized Grocery Retail Using Machine Learning: A Data-Driven Approach To Minimizing Stock-Outs And Waste., Dragos Andrei Ungureanu

ICT

Mid-sized grocery retailers face a persistent challenge in balancing on-shelf availability with minimizing spoilage of perishable goods. This dissertation addresses this issue by developing a data-driven forecasting and inventory simulation framework within Microsoft Fabric, leveraging scalable data ingestion, Spark-based processing, and advanced machine learning. Using multi-year transactional data enriched with holiday schedules, promotions, and macroeconomic indicators, the study compares classical ARIMA models with XGBoost to capture complex demand patterns. Rigorous hyperparameter tuning in a distributed environment demonstrates that XGBoost outperforms baseline models in terms of MAE and MAPE, particularly during promotion-driven spikes. Inventory simulations based on these forecasts reduce stock-outs …

Data-Driven Decarbonisation Strategy For Residential Buildings: A Q-Learning-Based Simulation Approach., Erdenechimeg Tserendorj

ICT

This study presents an AI-driven framework for optimising energy retrofit interventions in Irish residential buildings, combining Q-Learning (QL), surrogate models (ANN, RF), and a Genetic Algorithm (GA) optimiser. Q-Learning simulated sequential retrofit decisions, generating a dataset used to train surrogate models for predicting Building Energy Rating (BER) and CO₂ outcomes. The GA explored retrofit combinations to maximise BER improvement, CO₂ reduction, and financial returns. The framework identified strategies achieving up to 928 kWh/m² BER reduction and 1,563 kg CO₂ reduction per building, with strong ROI and payback within 15 years. The modular, interpretable pipeline demonstrates the practical value of reinforcement …

Enhancing Insider Threat Detection Through A Hybrid Approach Using Different Artificial Intelligence Techniques., Jose Roberto Da Silva Dure

ICT

Insider threats pose significant challenges in cybersecurity due to their origin from individuals with legitimate access. Traditional defenses often fail to detect malicious behavior embedded within normal activities. This study proposes a hybrid artificial intelligence framework that integrates unsupervised anomaly detection, supervised and ensemble learning, and deep learning to enhance insider threat detection. Using the CERT 4.1 dataset, features encompassing temporal, behavioral, network, and psychometric aspects were engineered. Anomaly detection models informed supervised and ensemble classifiers, while a multi-input deep learning architecture captured sequential and contextual patterns. Performance evaluation using ROC-AUC, precision, recall, F1-score, and cost-sensitive analysis demonstrates that the …

Enhancing Financial Fraud Detection Using Explainable Deep Learning Models On Simulated Big Data Architectures: A Comparative Analysis With Traditional Methods., Aoife Yang

ICT

Financial fraud poses a growing global challenge, driven by the rapid expansion of digital banking, e-commerce, and mobile payments. Traditional rule-based and early machine learning systems struggle to detect novel and sophisticated fraud patterns in real time. This research investigates the integration of deep learning, explainable artificial intelligence (XAI), and big data technologies to enhance financial fraud detection. A scalable data pipeline is proposed to process large volumes of transactional data, improve detection accuracy, and provide interpretable insights for stakeholders. The study highlights the potential of combining advanced AI techniques with explainability to strengthen the transparency, effectiveness, and trustworthiness of …

Enhancing Fake News And Rumor Detection Using Metadata, Context, And User Interaction With A Hybrid Gcn-Transformer., Lucas Romulo Zuin Gigli

ICT

The increasing influence of social media has significantly impacted how news spreads among users, making the detection of misinformation, including fake news and rumours, a critical task. Previous research has explored content-based and metadata-driven approaches, while recent advancements have leveraged Graph Neural Networks (GNNs) such as GCNs, GATs, and SAGE to analyse user interactions and propagation patterns. This thesis investigates the effectiveness of a Hybrid Graph-Transformer Convolutional Neural Network (GCN-Transformer) for fake news detection, combining graph-based learning with Transformer attention mechanisms. Through in-depth data analysis and advanced detection techniques, this model aims to enhance predictive performance and mitigate the spread …

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 …

Evaluating The Effectiveness Of Variational Mode Decomposition(Vmd)-Enhanced Hybrid Models For Forecasting Volatile Price And Indicator Time Series., Danny Allen

ICT

Forecasting volatile time series, such as commodity prices and market volatility indices, is critical for financial and operational decision-making. This study evaluates the impact of Variational Mode Decomposition (VMD) on hybrid forecasting models combining ARIMA, GARCH, and LSTM. Using gold, platinum, and VIX datasets, models were assessed via MAE, RMSE, and computational time. Results show that VMD improves ARIMA forecasts, and achieves optimal performance when combined with ARIMA-LSTM using performance weighting reducing MAE by 0.62-3.81 and reducing RMSE by 1.48-6.20. Conversely, VMD integration with ARIMA-GARCH and LSTM decreased accuracy. While VMD enhances predictive performance, it increases computational time substantially, increasing …

Discovering Latent Themes: Mixed-Methods Comparative Analysis Of Topic Extraction And Clustering., Laura Byrne

ICT

This study investigates whether clustering and topic modeling can uncover themes within the 167 verses of the King James Version of the Book of Esther. A standardized preprocessing pipeline was applied, and TF-IDF and sentence-embedding feature spaces were used to evaluate topic extraction (NMF, GSDMM, BERTopic, Top2Vec) and clustering (HDBSCAN, DBSCAN, Gaussian Mixtures, Agglomerative) using coherence, cluster validity, lexical distinctiveness, and cross-model similarity metrics. NMF provided the most interpretable topics, GSDMM yielded compact low-overlap topics, BERTopic offered entity-centered groupings, and Top2Vec highlighted broad thematic regions. Cross-model analysis revealed overlapping motifs, notably decree and banquet themes, but clusters and topics did …

Exploring Workforce Attrition In Early Childcare Sector Using Data Segmentation, Machine Learning And Artificial Neural Networks., Anna Fontani-Tankovska

ICT

This research presents a framework of workforce attrition exploration based on integration of data segmentation, feature selection and classification models. K-prototypes clustering and generation-based segmentation are applied to create data subsets processed using logistic regression, random forest, naïve Byes, and artificial neural networks. By segmenting data, this study aims at enhancing models classification capacity. To address data imbalance and improve models ability to identify minority class, synthetic minority oversampling technique (SMOTE) and adaptive synthetic sampling approach (ADASYN) are applied, with average recall rate improving from 0.39 to 0.61 (SMOTE) and 0.50 (ADASYN). Feature selection using Recursive Feature Elimination with SVC …

Exogenous Variables In Time Series Forecasting During Economic Volatility: A Cross-Sector And Cross-Crisis Evaluation., Orla Kavanagh

ICT

Economic disruptions pose challenges for time series forecasting, but also offer opportunities to evaluate the value of exogenous information. This study investigates the role of external indicators during the COVID-19 pandemic and the 2025 U.S. tariff shock, using data from Dell (technology) and Boeing (aerospace/manufacturing). ARIMA, SARIMA, and LSTM models were tested with candidate exogenous variables. Results indicate that the benefit of external signals is highly context-dependent: sector, disruption type, and forecast horizon all influence effectiveness. LSTM models generally excel at longer horizons with exogenous inputs, while ARIMA-based models perform better short-term. Findings emphasize that careful variable selection, ongoing evaluation, …