• Identified challenges in explainability techniques applied to the state-of-the-art deep learning models for phylogenetic trees.
• Studied graph-based encodings for phylogenetic trees to predict key parameters and presented my results at the MCEB Congress.
• Participated in the XVII scientific marathon as a co-author of the presentation “AI and its capacity to understand the generation and extinction of species”.
• Supervisor: Isabel Sanmartin.

• Conducted a comprehensive literature review, focusing on the application of AI and Large Language Models to enhance learning and educational methods.
• Learnt about the science of learning through research articles and the books Make it Stick and Ultralearning.
• Supervisor: Alejandro Martín.

• Utilised advanced models (Transformers, XGBoost, and ensemble methods) for churn prediction using an imbalanced dataset.
• Applied Bayesian optimisation and genetic algorithms for hyperparameter optimization using a custom metric to adapt model selection to the company’s needs.
• Created data analysis reports for data stored in multiple tables and more than one thousand columns in total. Some of them included visualizations with t-SNE.

GPA: 94% (best academic record award & 13 honor grades).

Thesis: Solving the Job Shop Scheduling Problem with Graph Neural Networks: A Customizable Reinforcement Learning Environment.

Tutor for incoming students during the first semesters of 2021 and 2022.

GPA: 97.4%

Courses included:

• Computational Intelligence
• Robotics
• Advanced Natural Language Processing
• Decision Analysis
• Data Visualisation
• Polish

Coursework:

• Uncertainty Quantification in Numerical Simulations