1. Introduction    

1.1. Introduction

1.2. Multivariate versus univariate models

1.3. Overview of the ten-step methodology  

2. Data Preprocessing

2.1. Introduction

2.2. Data Preprocessing

2.3. Download the original data

3. Dataset split   

3.1. Introduction

3.2. Polynomial Features

3.3. Dataset split

 4. Dataset scaling  

4.1. Introduction

4.2. Scaling the data and the features matrices  

5. Shallow Neural Networks

5.1. Introduction

5.2. Compiling the models

5.3. Fitting and drawing the models

5.4. Drawing in detail

5.5. Explanation of the activation function

5.6. Generating predictions

5.7. Test set errors

5.8. Training set errors

5.9. Overfitting analysis

5.10. Naive model test

5.11. Sensitivity analysis and hyperparameter tuning

5.12. Sensitivity analysis

5.13. Forecasts: theory and methodology

5.14. Generating the forecasts

5.15. Final selection of the models

6. Conclusion

6.1. Conclusions