Ce cours apparaît dans les formations suivantes :
• IÉSEG > MSc in Big Data Analytics for Business > Semester 2 > 2,00 ECTS

Pré requis

Algebra, inferential statistics, including (practical) knowledge of distributions, hypothesis testing, confidence intervals and the foundations of regression modeling

Objectifs du cours

At the end of the course, the student should be able to:
- master the forecasting process, its data considerations and business implementation strategies
- apply statistical and econometric methods (modeling, estimation, interpretation, forecasting) to obtain forecasts in practical settings in business and economics
- understand the statistical background of the methods commonly used for forecasting in business and economics, and assess the appropriateness of the methods for specific problems
- build econometric forecasting models using real data into a dedicated econometric software package and interpret the output correctly, including the managerial consequences of the obtained results
- communicate about an econometric forecasting analysis, using appropriate scientific jargon

These competencies and/or skills contribute to the following learning objectives
- 3.A Breakdown complex organizational problems using the appropriate methodology
- 3.B Propose creative solutions within an organization
- 5.A. Predict how business and economic cycles could affect organizational strategy
- 5.B Construct expert knowledge from cutting-edge information
- 7.A Demonstrate an expertise on key concepts, techniques and trends in their professional field
- 7.B Formulate strategically-appropriate solutions to complex and unfamiliar challenges in their professional field

Contenu du cours

• Forecasting in business and economics
• Basic tools for forecasting
• Exponential smoothing
• Time series decomposition
• ARIMA models
• Forecasting in practice

Modalités d'enseignement

Organisation du cours

Méthodes pédagogiques

• Coaching
• E-learning
• Interactive class
• Presentation
• Project work

Évaluation

Students individually prepare an empirical paper in which two recent and relevant time series are forecasted, using the techniques that have been discussed during the lectures. The first data set is provided by the lecturer, together with guiding questions. The second data set is selected by the student and analyzed according to a carefully selected forecasting process, taking data considerations and implementation issues into account. More details will be provided in the first lecture.

Bibliographie

• Hyndman, R.J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. -

  http://otexts.org/fpp2/

Ressources internet

• Forecasting: principles and practice