Pedro Alonso
About Pedro Alonso
Pedro Alonso is a Senior Data Scientist at eSpark Learning, specializing in Natural Language Processing, sentiment analysis, and text similarity. He has extensive experience in unsupervised and supervised learning techniques, data analysis, and building data-driven solutions.
Work at eSpark Learning
Pedro Alonso has been employed as a Senior Data Scientist at eSpark Learning since 2024. In this role, he focuses on Natural Language Processing tasks, including Sentiment Analysis and Text Similarity. His work is based in Chicago, Illinois, where he has contributed to various data-driven projects to enhance educational experiences.
Previous Experience at Afya
Before joining eSpark Learning, Pedro Alonso worked at Afya as a Senior Data Scientist from 2021 to 2024. During his tenure, he specialized in segmenting millions of users for marketing and personalization purposes using clustering algorithms. His experience at Afya contributed to his expertise in data science and analytics.
Education and Expertise
Pedro Alonso holds a Mestrado in Estatística from KU Leuven, where he studied from 2019 to 2022. He also earned a Bacharelado in Administração e Negócios from Universidade Federal do Rio de Janeiro, completing his studies from 2015 to 2018. His educational background provides a strong foundation for his work in data science, particularly in statistical analysis and business applications.
Technical Skills and Proficiencies
Pedro Alonso possesses extensive technical skills in data science, including proficiency in supervised and unsupervised learning techniques. He is experienced with algorithms such as KMeans, Random Forests, and XGBoost. His technical toolkit includes programming languages and libraries like Python, R, and SQL, as well as visualization tools such as PowerBI and Excel.
Contributions to Data Science
Throughout his career, Pedro Alonso has made significant contributions to data science projects. He created an AB testing framework that has facilitated the design of numerous tests. Additionally, he developed a classification algorithm to predict customer churn based on product usage data. His work has included building dashboards and reports for senior leadership, showcasing his ability to communicate complex data insights effectively.