Course Summary

This course equips students with a comprehensive understanding of time series forecasting methodologies. It covers essential concepts such as point forecasting, forecast intervals, errors, and uncertainty estimation. Students will explore statistical models like ARIMA, SARIMA, and ARIMAX, as well as exponential smoothing and decomposition methods. Advanced techniques, including deep learning models for forecasting, are also introduced, allowing students to practically implement, analyze, and comparatively evaluate forecasting methodologies in real-world applications.

Course Highlights

• Fundamental Concepts of Time Series Forecasting
• Exploratory Analysis and Decomposition Methods
• Exponential Smoothing Techniques
• ARIMA, SARIMA, and ARIMAX Models
• Deep Learning Models for Time Series Forecasting
• Comparative Evaluation and Model Validation
• Practical Implementation using R and Python

Instructors

• Prof. Ana Alexandra Antunes Figueiredo Martins
• Prof. Artur Jorge Ferreira

Learn More

For detailed syllabus, learning outcomes, assessment methods, and recommended bibliography, please refer to the official course documentation provided.