In the course, Learn Time Series Analysis and Forecasting, the student will be given an intensive overview of how to analyse and then make predictions on univariate and multivariate time series datasets.

The course is comprised of four sections, which are:-

1. Introduction to time series forecasting and analysis

2. Different time series methods to explore

3. Projects to work on

4. Kaggle competitions

The introduction to the course is comprised of five videos, covering ti me series analysis, statsmodels, and Facebook Prophet.

The different methods to be explored are comprised of:-

1. Baseline or lagged method

2. Holt Winters triple exponential smoothing method

3. Random walk method

4. Simple Average method

5. Moving average method

6. Auto Regression

7. ARIMAmethod

8. Simple exponential smoothing

9. Holt double exponential smoothing method

10. XGBoost Regressor

11. Random Forest method

12. Facebook Prophet

In addition to the classical time series forecasting methods, the course will cover how to predict on a time series dataset using machine learning and also Facebook Prophet, which is a newer library.

In the projects section of the course, the student will be given the code for a number of projects, which are:-

1. Tractor sales

2. Sickness at work

3. Waste collection

4. Exponential smoothing

5. Female births in California

6. Number of employees

7. Shampoo sales

8. SARIMEX

9. Energy consumption

10. An analysis of the spread of monkey pox

11. VAR

12. VARMA

In the final part of the course the student will be invited to enter a Kaggle competition relating to time series and the code for three past Kaggle competitions will be discussed.