Richie CottonSenior Data Evangelist, DataCamp · Ask me about data and AI upskilling

Forecasting Using R

Name: Forecasting Using R
Uploaded: 2019-02-12T18:08:22+00:00
Duration: 1 min 29 s
Channel: Richie Cotton
Description: In this introductory lecture for the DataCamp course "Forecasting Using R," Professor Rob Hyndman, the creator of the forecast package and…

12 Feb 2019 · 1 min

Watch on YouTube

1:29

In this introductory lecture for the DataCamp course "Forecasting Using R," Professor Rob Hyndman, the creator of the forecast package and editor-in-chief of the International Journal of Forecasting, outlines the course structure and learning objectives. He emphasizes that the course assumes basic R and introductory statistics knowledge but no prior experience with time series or forecasting. The curriculum begins with exploratory visualization tools to detect trend and seasonality, then covers simple benchmark forecasting methods and techniques for measuring forecast accuracy. The core of the course focuses on two major model families—exponential smoothing and ARIMA—each receiving a dedicated chapter. Finally, Hyndman previews advanced topics such as models for weekly and hourly data and the incorporation of external information into forecasts. The tone is instructional and enthusiastic, inviting learners to engage with the material and apply the forecast package throughout the course.

Chapters

Welcome to the course Forecasting Using R. I'm Rob Hyndman and I'll be your instructor for this course. I'm a professor of Statistics at Monash University in Melbourne, Australia, and I'm the Editor in Chief of the International Journal of Forecasting. I'm also an advisor to various businesses and governments on forecasting issues. You might know me as the author of the Forecast Package for R. We'll be using the forecast package as the basis for this Data Camp course. I've been working on it for nearly 15 years and I still have a lot of things I want to do to improve it. You're going to be learning about forecasting Time Series using R. I assume you already know a little bit about using R, as well as some introductory statistics, including regression. However, I won't assume you know anything about time series or forecasting. You'll start with some basic exploratory tools for visualizing time series in order to identify common patterns such as trend and seasonality. You'll learn a few simple forecasting methods that will be useful benchmarks against which you can compare the more complicated methods that you'll consider later in the course. You'll also learn how to measure forecast accuracy. There are two big classes of forecasting models that are used a Exponential smoothing and Arima models. You will spend a chapter on each of them. Finally, I want to show you some more advanced methods, including models for weekly and hourly data and how to introduce other information into your forecasts. I look forward to seeing you in the course.