Business Forecasting 2600-MSMdz2PIS

Lecture:
1. Definition of forecasts and simulation. Deterministic and stochastic simulation. Simulation examples.
2. Introduction to discrete event simulation – simple simulation, simulation on the crate. Random number generation. Sampling from probability distributions – inverse transform method.
3. Discrete event simulation – dynamic simulation and simulation of the next event.
4. Forecasting overview. Structural and non-structural models. Steps in forecasting. Testing forecast accuracy. An analysis of ex post and ex ante forecasting errors.
5. Naive forecasting models. Moving average forecasting method.
6. Exponential smoothing. Smoothing techniques – Brown’s, Holt’s and Winter’s methods. The choice of the smoothing parameters.
7. Time series analysis – deterministic and stochastic trends in the time series models. Stationary and non stationary time series.
8. Neural networks in forecasting.

Laboratory:
1. Using formulas in Excel – overview. Analysis with basic statistic.
2. Random numbers. Generating values from a statistical distribution. Building a worksheet-based simple simulation.
3. Discrete event simulation – steady-state models. Solving storage problem.
4. Discrete event simulation – dynamic simulations model changes in a system in response to input signals. Using dynamic simulation to improve production.
5. Dynamic simulation. Output analysis.
6. Time series forecasting rules. Naive models.
The implementations and limitations of naive models.
7. Moving average analysis. Measurement of forecasting error (ex ante and ex post). Introduction to optimization with the Excel Solver tool.
8. Exponential smoothing models – Brown's, Holt’s and Winter’s smoothing.
9. Time series forecasting models. Time series decomposition (seasonality, trend, error).
10. Project presentation.