Advanced Forecasting with Python: With State-of-the-Art-Models Including LSTMs, Facebook’s Prophet, and Amazon’s DeepAR

Table of Contents
About the Author
About the Technical Reviewer
Introduction
Part I: Machine Learning for Forecasting
	Chapter 1: Models for Forecasting
		Reading Guide for This Book
		Machine Learning Landscape
			Univariate Time Series Models
				A Quick Example of the Time Series Approach
			Supervised Machine Learning Models
				A Quick Example of the Supervised Machine Learning Approach
				Correlation Coefficient
			Other Distinctions in Machine Learning Models
				Supervised vs. Unsupervised Models
				Classification vs. Regression Models
				Univariate vs. Multivariate Models
		Key Takeaways
	Chapter 2: Model Evaluation for Forecasting
		Evaluation with an Example Forecast
		Model Quality Metrics
			Metric 1: MSE
			Metric 2: RMSE
			Metric 3: MAE
			Metric 4: MAPE
			Metric 5: R2
		Model Evaluation Strategies
			Overfit and the Out-of-Sample Error
			Strategy 1: Train-Test Split
			Strategy 2: Train-Validation-Test Split
			Strategy 3: Cross-Validation for Forecasting
				K-Fold Cross-Validation
				Time Series Cross-Validation
				Rolling Time Series Cross-Validation
		Backtesting
		Which Strategy to Use for Safe Forecasts?
		Final Considerations on Model Evaluation
		Key Takeaways
Part II: Univariate Time Series Models
	Chapter 3: The AR Model
		Autocorrelation: The Past Influences the Present
			Compute Autocorrelation in Earthquake Counts
			Positive and Negative Autocorrelation
		Stationarity and the ADF Test
		Differencing a Time Series
		Lags in Autocorrelation
			Partial Autocorrelation
			How Many Lags to Include?
		AR Model Definition
		Estimating the AR Using Yule-Walker Equations
			The Yule-Walker Method
			Train-Test Evaluation and Tuning
		Key Takeaways
	Chapter 4: The MA Model
		The Model Definition
		Fitting the MA Model
		Stationarity
		Choosing Between an AR and an MA Model
		Application of the MA Model
		Multistep Forecasting with Model Retraining
		Grid Search to Find the Best MA Order
		Key Takeaways
	Chapter 5: The ARMA Model
		The Idea Behind the ARMA Model
		The Mathematical Definition of the ARMA Model
		An Example: Predicting Sunspots Using ARMA
		Fitting an ARMA(1,1) Model
		More Model Evaluation KPIs
		Automated Hyperparameter Tuning
		Grid Search: Tuning for Predictive Performance
		Key Takeaways
	Chapter 6: The ARIMA Model
		ARIMA Model Definition
		Model Definition
		ARIMA on the CO2 Example
		Key Takeaways
	Chapter 7: The SARIMA Model
		Univariate Time Series Model Breakdown
		The SARIMA Model Definition
		Example: SARIMA on Walmart Sales
		Key Takeaways
Part III: Multivariate Time Series Models
	Chapter 8: The SARIMAX Model
		Time Series Building Blocks
		Model Definition
		Supervised Models vs. SARIMAX
		Example of SARIMAX on the Walmart Dataset
		Key Takeaways
	Chapter 9: The VAR Model
		The Model Definition
			Order: Only One Hyperparameter
			Stationarity
			Estimation of the VAR Coefficients
		One Multivariate Model vs. Multiple Univariate Models
		An Example: VAR for Forecasting Walmart Sales
		Key Takeaways
	Chapter 10: The VARMAX Model
		Model Definition
		Multiple Time Series with Exogenous Variables
		Key Takeaways
Part IV: Supervised Machine Learning Models
	Chapter 11: The Linear Regression
		The Idea Behind Linear Regression
		Model Definition
		Example: Linear Model to Forecast CO2 Levels
		Key Takeaways
	Chapter 12: The Decision Tree Model
		Mathematics
			Splitting
			Pruning and Reducing Complexity
		Example
		Key Takeaways
	Chapter 13: The kNN Model
		Intuitive Explanation
		Mathematical Definition of Nearest Neighbors
			Combining k Neighbors into One Forecast
			Deciding on the Number of Neighbors k
			Predicting Traffic Using kNN
			Grid Search on kNN
			Random Search: An Alternative to Grid Search
		Key Takeaways
	Chapter 14: The Random Forest
		Intuitive Idea Behind Random Forests
		Random Forest Concept 1: Ensemble Learning
			Bagging Concept 1: Bootstrap
			Bagging Concept 2: Aggregation
		Random Forest Concept 2: Variable Subsets
		Predicting Sunspots Using a Random Forest
		Grid Search on the Two Main Hyperparameters of the Random Forest
		Random Search CV Using Distributions
			Distribution for max_features
			Distribution for n_estimators
			Fitting the RandomizedSearchCV
		Interpretation of Random Forests: Feature Importance
		Key Takeaways
	Chapter 15: Gradient Boosting with XGBoost and LightGBM
		Boosting: A Different Way of Ensemble Learning
		The Gradient in Gradient Boosting
		Gradient Boosting Algorithms
		The Difference Between XGBoost and LightGBM
		Forecasting Traffic Volume with XGBoost
		Forecasting Traffic Volume with LightGBM
		Hyperparameter Tuning Using Bayesian Optimization
			The Theory of Bayesian Optimization
			Bayesian Optimization Using scikit-optimize
		Conclusion
		Key Takeaways
Part V: Advanced Machine and Deep Learning Models
	Chapter 16: Neural Networks
		Fully Connected Neural Networks
		Activation Functions
		The Weights: Backpropagation
		Optimizers
		Learning Rate of the Optimizer
		Hyperparameters at Play in Developing a NN
		Introducing the Example Data
		Specific Data Prep Needs for a NN
			Scaling and Standardization
			Principal Component Analysis (PCA)
		The Neural Network Using Keras
		Conclusion
		Key Takeaways
	Chapter 17: RNNs Using SimpleRNN and GRU
		What Are RNNs: Architecture
		Inside the SimpleRNN Unit
		The Example
		Predicting a Sequence Rather Than a Value
		Univariate Model Rather Than Multivariable
		Preparing the Data
		A Simple SimpleRNN
		SimpleRNN with Hidden Layers
		Simple GRU
		GRU with Hidden Layers
		Key Takeaways
	Chapter 18: LSTM RNNs
		What Is LSTM
		The LSTM Cell
		Example
		LSTM with One Layer of 8
		LSTM with Three Layers of 64
		Conclusion
		Key Takeaways
	Chapter 19: The Prophet Model
		The Example
		The Prophet Data Format
		The Basic Prophet Model
		Adding Monthly Seasonality to Prophet
		Adding Holiday Data to Basic Prophet
		Adding an Extra Regressor to Prophet
		Tuning Hyperparameters Using Grid Search
		Key Takeaways
	Chapter 20: The DeepAR Model
		About DeepAR
		Model Training with DeepAR
		Predictions with DeepAR
		Probability Predictions with DeepAR
		Adding Extra Regressors to DeepAR
		Hyperparameters of the DeepAR
		Benchmark and Conclusion
		Key Takeaways
	Chapter 21: Model Selection
		Model Selection Based on Metrics
		Model Structure and Inputs
		One-Step Forecasts vs. Multistep Forecasts
		Model Complexity vs. Gain
		Model Complexity vs. Interpretability
		Model Stability and Variation
		Conclusion
		Key Takeaways
Index