Mario Prieto

Passionate data scientist leading projects, solving complex problems, and extracting valuable insights from data, driven by integrity, innovation, and a commitment to making a positive impact.

2021-Today 

Senior Data Scientist

Madrid, Spain Ministry of Defense 

Contributed to projects in NLP, anomaly detection, and computer vision using LLM, deep learning, and traditional machine learning. Key tasks include: 

• Studied and analyzed data employing unsupervised methods: clustering, dimensional reduction, anomaly detection, and association mining. 

• Leveraged APIs for data retrieval, crafted web scrapers, and executed data wrangling to ensure optimal data quality and accessibility. 

• Utilized Large Language Models (LLMs) for diverse NLP tasks: text translation, summarization, QA, sentiment analysis, and text classification.

 • Participated in the fine-tuning of Large Language Models, such as BERT or ViT, for optimal performance. 

• Supported strategic decision-making with data mining and interactive visualizations using Kibana. 

• Enhanced efficiency in a sentence classification model using data augmentation, LSTM neural network, and XGBoost algorithm. 

• Designed and implemented efficient big data pipelines within a Spark environment using PySpark, optimizing data workflows. 

• Upheld data governance practices to maintain data integrity, security, and GDPR compliance. 

2020-2021

Data Steward

Málaga, Spain Polytechnic University of Madrid

 Managed the quality, consistency, and security of rare disease data. Implemented data standards and ensured compliance with FAIR principles. Collaborated with teams to promote data management best practices. Upheld responsible data handling and privacy protection, aligning with GDPR guidelines to safeguard user information. 

2020-2021 

Python Developer 

Málaga, Spain FAIR Data Systems 

In charge of creating ad-hoc solutions to address unique business challenges. This involved designing, coding, and implementing custom Python applications to automate processes. 

2015-2019 

Data Scientist - Researcher

Madrid, Spain Polytechnic University of Madrid 

Contributed to the ’Quality and Trust from Provenance in E-Science’ project, aiming to enhance data and result quality through provenance analysis. Specialized in NLP with expertise in sentiment analysis, text classification, and text mining. Also proficient in clustering techniques and deep learning. Designed and deployed a ML model achieving 86% accuracy in assigning a ’certainty’ sentiment field.

2023 

M.Sc. Expert in Data Science and Big Data. Madrid, Spain 

Datahack School

2019

Ph.D. NLP/Text Mining field. Madrid, Spain 

Polytechnic University of Madrid 

Degree: 10/10 Cum Laude

2016 

M.Sc. Bioinformatics and Computational Biology. Madrid, Spain 

National School of Health ISCIII 

2014 

B.Sc. Biology. Seville, Spain

University of Seville