Academic Projects

Projects that connect business problems, data, systems and measurable impact

These projects reflect my ability to analyse real-world business challenges, design structured solutions, work with data, document requirements, compare technical approaches and translate results into practical business value.

MSc Research Thesis 2025

AI-Powered Food Recognition Using CNNs

Designed and evaluated a computer vision solution to identify perishable food items in restaurant environments, with the aim of reducing pre-consumption food waste through smarter inventory visibility.

39,962 food images prepared
10,000 images trained per model
2 CNNs ResNet50 & InceptionV3

What I did

Problem Framing Identified a practical sustainability problem in restaurants: food being wasted before consumption due to poor storage visibility.
Dataset Preparation Worked with a large food image dataset, cleaned metadata, validated image files, mapped class labels and created a usable training dataset.
Model Development Built transfer learning pipelines using TensorFlow/Keras with ResNet50 and InceptionV3 for multi-class food image classification.
Training Strategy Used ImageDataGenerator, data augmentation, batch-size tuning, Google Colab GPU resources, ModelCheckpoint and EarlyStopping.
Performance Evaluation Compared models using top-1 accuracy, top-3 accuracy, training loss and validation loss to understand accuracy and deployability trade-offs.
Business Value Positioned the solution as a foundation for AI-enabled fridge monitoring, stock awareness and waste reduction in food service operations.
Python TensorFlow Keras ResNet50 InceptionV3 Google Colab Computer Vision Data Preprocessing
Project Management Simulation 2024

Decision Support System for Fraud Detection

Designed a project management and business analysis framework for an AI-powered Decision Support System that detects suspicious financial transactions using machine learning, rule-based logic and real-time monitoring.

26 Weeks delivery roadmap
8 Sprints Agile release plan
€571,975 estimated budget

What I did

Business Case Defined the need for a fraud detection system to reduce financial losses, improve response time and support regulatory compliance.
Requirements Analysis Documented business, solution, transition, project and quality requirements, including dashboards, risk scoring and real-time alerts.
Agile Planning Created sprint-based delivery planning, milestones, release plans and Jira-style roadmap tracking across the full project lifecycle.
Project Controls Built cost estimates, contingency planning, earned value management analysis, acceptance criteria and change control documentation.
Stakeholder Management Prepared RACI matrix, stakeholder analysis, communication matrix, escalation approach and team resource allocation plan.
Risk Management Created a risk register covering technical, schedule, cost, compliance, resource and security risks with mitigation actions.
Business Analysis Jira Agile Risk Management RACI EVM Requirements Fraud Detection