TRAINING

Demand forecast models with R

— Through the sales of goods or services, Demand Forecasting is one of the key challenges in operational planning and in designing facilities for the long-term. This course provides tools to master R software used in the context of demand forecasting.

COURSE OBJECTIVES

• Develop skills in R software, from getting started to deploying forecasting modules.
• Gain a proven methodology for data analysis and development of a demand forecasting model.
• Learn about statistical techniques for forecasting: know the main ranges of models, their advantages and disadvantages, as well as the link with the business expertise.

TARGET AUDIENCE

This course is intended for people who work with a set of data (e.g., business analysts) and who are looking to improve their skills with a tool that allows them to perform advanced analyses.

INSTRUCTORS

The speakers are Artelys consultants with a sound knowledge of R software and issues related to demand management.

PROGRAM

Getting started with R software
• Main features and advantages.
• Description of the syntax and the most useful keywords.
• Good programming practices in R.
• Installation of the software and the working environment.

Illuminating the data and the problem
• Getting to grips with the data by visualizing the chronicles.
• From raw data to usable data (data preprocessing methods).
• Identification of the structuring characteristics of the data (numerical and graphic indicators, seasonality, explanatory factors).
• Definition of the problem, the stakes, and the quality criteria of the forecasts.

Build a relevant demand model
• Which models should be considered given the characteristics of the data? Presentation of several classical models: autoregressive models (S)AR(I)MA(X), linear models.
• Implementation of the different models with the R software.
• How to choose a good model: analysis of the quality of the forecasting results (fitting performance, generalization).

To go further
• Other types of models (frequency models).
• How to make relevant graphs (ggplot package).
• How to maintain in time your developments in R.