Forecasting time series data with Prophet : build, improve, and optimize time series forecasting models using Meta's advanced forecasting Tool / Greg Rafferty.

Format:

Book

Author/Creator:

Rafferty, Greg, author.

Language:

English

Subjects (All):

Time-series analysis--Data processing.

Time-series analysis.

Python (Computer program language).

Machine learning.

Physical Description:

1 online resource (282 pages)

Edition:

Second edition.

Place of Publication:

Birmingham, England : Packt Publishing Ltd., [2023]

Biography/History:

Rafferty Greg: Greg Rafferty is a data scientist at Google in San Francisco, California. With over a decade of experience, he has worked with many of the top firms in tech, including Facebook (Meta) and IBM. Greg has been an instructor in business analytics on Coursera and has led face-to-face workshops with industry professionals in data science and analytics. With both an MBA and a degree in engineering, he is able to work across the spectrum of data science and communicate with both technical experts and non-technical consumers of data alike.

Summary:

This book will help you get to grips with time series forecasting using the leading open source forecasting tool, Prophet. You'll learn how to implement Prophet's advanced features to build forecasting models and understand why and how to modify each of the default parameters to improve results.

Contents:

Cover

Title Page

Copyright

Contributors

Table of Contents

Preface

Part 1: Getting Started with Prophet

Chapter 1: The History and Development of Time Series Forecasting

Understanding time series forecasting

The problem with dependent data

Moving averages and exponential smoothing

ARIMA

ARCH/GARCH

Neural networks

Prophet

Recent developments

NeuralProphet

Google's "robust time series forecasting at scale"

LinkedIn's Silverkite/Greykite

Uber's Orbit

Summary

Chapter 2: Getting Started with Prophet

Technical requirements

Installing Prophet

Installation on macOS

Installation on Windows

Installation on Linux

Building a simple model in Prophet

Interpreting the forecast DataFrame

Understanding components plots

Chapter 3: How Prophet Works

Facebook's motivation for building Prophet

Analyst-in-the-loop forecasting

The math behind Prophet

Linear growth

Logistic growth

Seasonality

Holidays

Part 2: Seasonality, Tuning, and Advanced Features

Chapter 4: Handling Non-Daily Data

Using monthly data

Using sub-daily data

Using data with regular gaps

Chapter 5: Working with Seasonality

Understanding additive versus multiplicative seasonality

Controlling seasonality with the Fourier order

Adding custom seasonalities

Adding conditional seasonalities

Regularizing seasonality

Global seasonality regularization

Local seasonality regularization

Chapter 6: Forecasting Holiday Effects

Adding default country holidays

Adding default state/province holidays

Creating custom holidays

Creating multi-day holidays

Regularizing holidays

Global holiday regularization.

Individual holiday regularization

Chapter 7: Controlling Growth Modes

Applying linear growth

Understanding the logistic function

Saturating forecasts

Increasing logistic growth

Non-constant cap

Decreasing logistic growth

Applying flat growth

Creating a custom trend

Chapter 8: Influencing Trend Changepoints

Automatic trend changepoint detection

Default changepoint detection

Regularizing changepoints

Specifying custom changepoint locations

Chapter 9: Including Additional Regressors

Adding binary regressors

Adding continuous regressors

Interpreting the regressor coefficients

Chapter 10: Accounting for Outliers and Special Events

Correcting outliers that cause seasonality swings

Correcting outliers that cause wide uncertainty intervals

Detecting outliers automatically

Winsorizing

Standard deviation

The moving average

Error standard deviation

Modeling outliers as special events

Modeling shocks such as COVID-19 lockdowns

Chapter 11: Managing Uncertainty Intervals

Modeling uncertainty in trends

Modeling uncertainty in seasonality

Part 3: Diagnostics and Evaluation

Chapter 12: Performing Cross-Validation

Performing k-fold cross-validation

Performing forward-chaining cross-validation

Creating the Prophet cross-validation DataFrame

Parallelizing cross-validation

Chapter 13: Evaluating Performance Metrics

Understanding Prophet's metrics

Mean squared error

Root mean squared error

Mean absolute error

Mean absolute percent error

Median absolute percent error.

Symmetric mean absolute percent error

Coverage

Choosing the best metric

Creating a Prophet performance metrics DataFrame

Handling irregular cut-offs

Tuning hyperparameters with grid search

Chapter 14: Productionalizing Prophet

Saving a model

Updating a fitted model

Making interactive plots with Plotly

Plotly forecast plot

Plotly components plot

Plotly single component plot

Plotly seasonality plot

Index

About Packt

Other Books You May Enjoy.

Notes:

Includes index.

Description based on print version record.

Description based on publisher supplied metadata and other sources.

ISBN:

9781837635504

1837635501

OCLC:

1375297109