Advanced Forecasting with Python

Cover all the machine learning techniques relevant for forecasting problems, ranging from univariate and multivariate time series to supervised learning, to state-of-the-art deep forecasting models such as LSTMs, recurrent neural networks, Facebook’s open-source Prophet model, and Amazon’s DeepAR model.

Rather than focus on a specific set of models, this book presents an exhaustive overview of all the techniques relevant to practitioners of forecasting. It begins by explaining the different categories of models that are relevant for forecasting in a high-level language. Next, it covers univariate and multivariate time series models followed by advanced machine learning and deep learning models. It concludes with reflections on model selection such as benchmark scores vs. understandability of models vs. compute time, and automated retraining and updating of models.

Each of the models presented in this book is covered in depth, with an intuitive simple explanation of the model, a mathematical transcription of the idea, and Python code that applies the model to an example data set.

Reading this book will add a competitive edge to your current forecasting skillset. The book is also adapted to those who have recently started working on forecasting tasks and are looking for an exhaustive book that allows them to start with traditional models and gradually move into more and more advanced models.

WHAT YOU WILL LEARN

* Carry out forecasting with Python
* Mathematically and intuitively understand traditional forecasting models and state-of-the-art machine learning techniques
* Gain the basics of forecasting and machine learning, including evaluation of models, cross-validation, and back testing
* Select the right model for the right use case

Who This Book Is For

The advanced nature of the later chapters makes the book relevant for applied experts working in the domain of forecasting, as the models covered have been published only recently. Experts working in the domain will want to update their skills as traditional models are regularly being outperformed by newer models.

Joos is a data scientist, with over five years of industry experience in developing machine learning tools, of which a large part is forecasting models. He currently works at Disneyland Paris where he develops machine learning for a variety of tools. His experience in writing and teaching have motivated him to make this book on advanced forecasting with Python.

PART I: Machine Learning for Forecasting

Chapter 1: Models for Forecasting

Chapter Goal: Explains the different categories of models that are relevant for forecasting in high level language

No pages: 10

Sub -Topics

1. Time series models

2. Supervised vs unsupervised models

3. Classification vs regression models

4. Univariate vs multivariate models

Chapter 2: Model Evaluation for Forecasting

Chapter Goal: Explains model evaluation with specific adaptations to keep in mind for forecasting

No pages: 15

Sub -Topics

1. Train test split

2. Cross validation for forecasting

3. Backtesting

PART II: Univariate Time Series Models

Chapter 3: The AR Model

Chapter Goal: explain the AR model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding AR model

2. Mathematical explanation of the AR model3. Worked out Python forecasting example with the AR model

Chapter 4: The MA model

Chapter Goal: explain the MA model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding MA model

2. Mathematical explanation of the MA model

3. Worked out Python forecasting example with the MA model

Chapter 5: The ARMA model

Chapter Goal: explain the ARMA model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding ARMA model

2. Mathematical explanation of the ARMA model

3. Worked out Python forecasting example with the ARMA model

Chapter 6: The ARIMA model

Chapter Goal: Explains the ARIMA model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding ARIMA model

2. Mathematical explanation of the ARIMA model

3. Worked out Python forecasting example with the ARIMA model

Chapter 7: The SARIMA Model

Chapter Goal: Explains the SARIMA model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding SARIMA model

2. Mathematical explanation of the SARIMA model

3. Worked out Python forecasting example with the SARIMA model

PART III: Multivariate Time Series Models

Chapter 8: The VAR model

Chapter Goal: Explains the VAR model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding VAR model

2. Mathematical explanation of the VAR model

3. Worked out Python forecasting example with the VAR model

Chapter 9: The Bayesian VAR model

Chapter Goal: Explains the Bayesian VAR model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding Bayesian VAR model

2. Mathematical explanation of the Bayesian VAR model

3. Worked out Python forecasting example with the Bayesian VAR model

PART IV: Supervised Machine Learning Models

Chapter 10: The Linear Regression model

Chapter Goal: Explains the Linear Regression model (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding Linear Regression model

2. Mathematical explanation of the Linear Regression model

3. Worked out Python forecasting example with the Linear Regression model

Chapter 11: The Decision Tree model

Chapter Goal: Explains the Decision Tree model (intuitively, mathematically and give Python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding Decision Tree model

2. Mathematical explanation of the Decision Tree model

3. Worked out Python forecasting example with the Decision Tree model

Chapter 12: The k-Nearest Neighbors VAR model

Chapter Goal: explain the k-Nearest Neighbors (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding k-Nearest neighbors model

2. Mathematical explanation of the k-Nearest neighbors model

3. Worked out Python forecasting example with the k-Nearest neighbors model

Chapter 13: The Random Forest Model

Chapter Goal: explain the Random Forest (intuitively, mathematically and give python application with code and data set)

No pages: 8

Sub -Topics

1. Understanding Random Forest model

2. Mathematical explanation of the Random Forest model

3. Worked out Python forecasting example with the Random Forest model

Chapter 14: The XGBoost model

Chapter Goal: Explains the XGBoost model (intuitively, mathematically and give python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding XGBoost model

2. Mathematical explanation of the XGBoost model

3. Worked out Python forecasting example with the XGBoost model

Chapter 15: The Neural Network model

Chapter Goal: Explains the Neural Network model (intuitively, mathematically and give python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding Neural Network model

2. Mathematical explanation of the Neural Network model

3. Worked out Python forecasting example with the Neural Network model

Part V: Advanced Machine and Deep Learning Models

Chapter 16: Recurrent Neural Networks

Chapter Goal: Explains Recurrent Neural Networks (intuitively, mathematically and give python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding Recurrent Neural Networks

2. Mathematical explanation of Recurrent Neural Networks

3. Worked out Python forecasting example with Recurrent Neural Networks

Chapter 17: LSTMs

Chapter Goal: Explains LSTMs (intuitively, mathematically and give python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding LSTMs

2. Mathematical explanation of LSTMs

3. Worked out Python forecasting example with LSTMs

Chapter 18: Facebook’s Prophet model

Chapter Goal: Explains Facebook’s Prophet model (intuitively, mathematically and give Python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding Facebook’s Prophet model

2. Mathematical explanation of Facebook’s Prophet model

3. Worked out Python forecasting example with Facebook’s Prophet model

Chapter 19: Amazon’s DeepAR Model

Chapter Goal: Explains Amazon’s DeepAR model (intuitively, mathematically and give python application with code and data set)

No pages: 10

Sub -Topics1. Understanding Amazon’s DeepAR model

2. Mathematical explanation of Amazon’s DeepAR model

3. Worked out Python forecasting example with Amazon’s DeepAR model

Chapter 20: Deep State Space Models

Chapter Goal: Explains Deep State Space models (intuitively, mathematically and give Python application with code and data set)

No pages: 10

Sub -Topics

1. Understanding Deep State Space models

2. Mathematical explanation of Deep State Space models

3. Worked out Python forecasting example with Deep State Space models

Chapter 21: Model selection

Chapter Goal: Give elements to select the best model for a specific situation

No pages: 16

Sub -Topics

1. Benchmark scores vs understandability of models vs compute time

2. Black swan outlier problems3. Automated retraining and updating of models

4. Conclusion