Course information

The course provides a comprehensive overview of modern forecasting techniques, covering both statistical and non-statistical methods. Its primary objective is to equip students with the knowledge and skills necessary to understand, evaluate, design, and implement effective forecasting procedures. The course emphasizes the extrapolation of time series, including: Fundamental time series analysis, Time series features, Smoothing techniques (moving averages), Decomposition methods, Identification and treatment of special events, Classification of Forecasting methods, Model selection, Forecast accuracy evaluation and monitoring, Exponential smoothing models (Simple, Holt, Damped), Linear regression models, ARIMA models, Theta method, Intermitted demand forecasting methods, Long-term and scenario forecasting, Judgmental forecasting, Forecasting competitions and benchmarks, Hierarchical forecasting, Forecasting with machine learning. In addition, the course highlights the practical use of IT systems to support forecasting activities. By the end of the course, students will have acquired both theoretical foundations and practical competencies in business forecasting. To support this learning, the course integrates traditional lectures with exercises and practical training.