Time Series Forecasting Part 3 - Vector Auto Regression

Go to main | Course Page

Section 1: VAR

  1. What is VAR and When can we use it?
  2. Download Resources
  3. Intuition behind VAR model formula
  4. Building VAR model in Python
  5. Import Dataset
  6. Visualize the time series
  7. Testing Causation using Granger’s Causality Test
  8. Cointegration Test
  9. Split the series into training and testing data
  10. Check for the stationary and make Time Series Stationary
  11. How to select the order (p) of VAR model
  12. Train the VAR model of selected order
  13. Check for serial correlation of residual (errors) using Durbin Watson Statistics
  14. How to forecast VAR model using stats model
  15. Invert the transformation to get the real forecast
  16. Plot of Forecast vs Actual
  17. Evaluate the forecast
  18. VARMA Model
  19. VARMAX with Exogenous Data
  20. Auto ARIMA on VARMA for Model Selection

Section 2: Practical Advise for succeeding in Time Series Project

  1. Align your forecast with working group ofshareholders
  2. Directions matters more
  3. Choice of Evaluation Matric
  4. Set realistic success criteria
  5. Educate your Stakeholders (Though they might not always listen)
  6. Explain your forecast
  7. Explain drop in the forecast after going live. Have root cause analysis mechanism involving domain expert
Report abuse