Inteligencia de Datos

Advanced data-science course analyzing the trends and paradigms of data science — its mathematical foundations and the development of models — to understand and carry out the full life cycle of a data-science project. Group A · Fall 2026 (17 weeks · 68 hours). Prerequisites: multivariable calculus, nonlinear optimization, linear algebra, probability, and structured programming (Python).

📄 Course study guide / Guía de estudio (PDF)

Learning goals / Fines de aprendizaje

1. Study and analyze the formulation of more complex machine-learning models widely used in the literature and industry.
2. Implement the studied models on diverse datasets from repositories, interpret the results, and improve model performance through analysis.
3. Learn to use different Python tools to implement the models seen in class.
4. Analyze and understand why certain models are used in certain applications.
5. Understand the life cycle of a data project and apply it to a mock problem.
6. Study design patterns used when training machine-learning models.

Syllabus / Temario

1. Máquinas de Vectores de Soporte (SVM)
   • Clasificación lineal, margen suave y clasificación no lineal
   • Clasificación multiclase y ejemplos de aplicación
2. Árboles de Decisión
   • Casos de clasificación y de regresión, con ejemplos de aplicación
3. Ensemble Learning
   • Voting classifiers
   • Bagging, Pasting y Bosques Aleatorios
   • Boosting (AdaBoost) y ejemplos de aplicación
4. Ciclo de vida de un proyecto de ciencia de datos
5. Patrones de diseño en Machine Learning
   • Patrones de representación de datos
   • Patrones de representación de problemas
   • Patrones de entrenamiento de modelos
6. Simulacro de un proyecto de Machine Learning
   • Repositorios de datos
   • Entrenamiento de modelos aplicado a problemas
   • Presentación de resultados
7. Estrategias de despliegue de modelos de Machine Learning (tentativo)
8. Agentes (tentativo)

Coursework / Actividades

• Lectures with slide decks synthesizing each topic.
• Hands-on labs in Google Colab implementing data-science algorithms; datasets come from public repositories or are built via APIs (Twitter API, NYT API, etc.) or web scraping.
• Readings of scientific articles on applications, paradigms, and philosophy of data science.
• A final project simulating the full workflow of a real-world ML project.
• Spanish Wikipedia article on a machine-learning / data-science topic of the student’s choice, evaluated in three stages (two drafts + final published article).

Assessment / Evaluación

| Instrument | Weight | |—|—| | Homework & computing labs | 25% | | Wikipedia project (3 stages: 5% + 5% + 5%) | 15% | | Assessment 1 (written exam) | 20% | | Assessment 2 | 20% | | Assessment 3 (final project) | 20% | | Total | 100% |

Key dates / Fechas importantes

• First day of classes: August 10, 2026
• First exam: September 24, 2026
• Wikipedia project — 1st draft: October 8, 2026
• Second assessment: October 22, 2026
• Wikipedia project — 2nd draft: November 3, 2026
• Wikipedia project — final & final project due: December 1, 2026
• Grades submitted: December 3, 2026
• Last day of classes: December 4, 2026

Suggested bibliography

Primary texts (★):

• ★ Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd ed.). O’Reilly.
• ★ Lakshmanan, V., Robinson, S., & Munn, M. (2020). Machine Learning Design Patterns: Solutions to Common Challenges in Data Preparation, Model Building, and MLOps. O’Reilly.

Additional references:

• Abu-Mostafa, Y. S., Magdon-Ismail, M., & Lin, H.-T. (2012). Learning from Data: A Short Course. AMLBook.
• Hastie, T., Tibshirani, R., & Friedman, J. H. (2009). The Elements of Statistical Learning. Springer.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
• Müller, A. C., & Guido, S. (2016). Introduction to Machine Learning with Python. O’Reilly.
• Calin, O. (2020). Deep Learning Architectures: A Mathematical Approach. Springer.