Online Applied Forecasting:
Improving the Accuracy and Value of Your Predictions

Blockchain Courses

Applied Forecasting Course

Duration Workload Mode of Study Live Q&A
6 weeks 10h/week Online training Wednesdays
at 18:00 (CY time)

Why Register?

About the Course



The M Applied Forecasting Course is a six week online course, (next intake 19 October 2020) covering all types of forecasting in both time series and regression, offering concrete insight to businesses on how to improve their accuracy realistically estimating the uncertainty in their forecasts and its implications to risk. In addition to the traditional forecasting methods, newer ones will be presented like Machine Deep and Cross Learning.

The most important advantage of the course is its emphasis on hands-on learning by encouraging participants to use actual data to both predict and estimate the uncertainty of their forecasts and its implication to risk. This course will offer students the opportunity to harness 40 years of Professor Makridakis knowledge and experience and master forecasting, in six weeks. In addition, Dr. Evangelos Spiliotis will present the R popular forecasting software and how they can be used, while Dr. Cirillo will lecture on fat-tails and their implications to forecasting and uncertainty. 

Course Outline

Session 1: Time Series Decomposition:

Seasonality, Trend-Cycle and Randomness

Session 2: Identifying Patterns/Relationships in the Data:

The Stat and the ML Approaches to forecasting.

Session 3: Graphical and Data Analysis Using the R* and Other Software Packages** 

Session 4: Forecasting and Uncertainty

*There will be tutorial sessions on how to use R to obtain the required forecasts
**There will also be a tutorial session of how to use Python

Session 5: The M Competitions:

The Use of Benchmarks, Simple vs. Sophisticated Methods, Combining Forecasts, Costs versus Accuracy 

Session 6: Exponential Smoothing Models and the Theta Method

Session 7: Regression Methods

Session 8: ML, DL, CL and Hybrid Models (ML: Machine Learning, DL: Deep Learning, CL: Cross Learning)

Session 9: Statistical 

Session 10: ML and DL

Session 11: Fat-Tailed Uncertainty and related risk

Session 12: Forecasting for:

  • Inventories (Preliminary Findings of the M5 Competition)
  • Sales and Operations (S&OPS)
  • Budgets
  • Long-Term Growth and Strategy
  • Preliminary Findings of the M5 Competition

What Will You Learn?

The course will last six weeks and cover among other topics the following:

  • Where to start and how to apply forecasting in your business
  • Estimating the future uncertainty in your predictions and taking concrete actions to deal with such uncertainty
  • Time Series forecasting and its use, utilizing available, free software programs
  • Using regression Models and exploiting its planning value

  • Neural networks, deep learning and hybrid forecasting models and their usefulness

  • Improving forecasting accuracy through the combination of forecasts

  • Exploiting the findings of the M Competitions to improve the forecasting function of your organization

  • Using your own data and available/free software programs to forecast your own series

  • Finding out how to use such free software in your own firm

Who Should Take This Course?

The course is designed for executives in charge of finance, marketing, selling and operations as well as consultants. Key applications covered in this course are from the above areas using case studies to illustrate their usage. Participants will acquire a practical understanding of how forecasting can help them to improve the accuracy of their predictions, and what they need to do in practice to reap maximum benefits.