Modern Time Series Forecasting with Python: Master industry-ready time series forecasting using modern machine learning

[LeeAndro]

English | 2022 | ISBN: ‎ 1803246804 | 552 pages | True PDF EPUB | 47.85 MB

Build real-world series forecasting systems which scale to millions of series by mastering and applying modern concepts in machine learning and deep learning
Key Features

Explore industry-tested machine learning techniques to forecast millions of series
Get started with the revolutionary paradigm of global forecasting models
Learn new concepts by applying them to real-world datasets of energy forecasting

Book Description

We live in a serendipitous era where the explosion in the quantum of data collected and renewed interest in data-driven techniques like machine learning (ML) has changed the landscape of analytics and with it series forecasting.​

This book attempts to take you beyond the commonly used classical statistical methods like ARIMA and introduce to you the latest techniques from the world of ML.

The book is a comprehensive guide to analyzing, visualizing, and creating state-of-the-art forecasting systems, complete with common topics like ML and deep learning (DL), and rarely touched upon topics like global forecasting models, cross-validation strats, and forecast metrics. We start off with the basics of data handling and visualization and classical statistical methods and very soon move on to ML and DL models for series forecasting.

By the end of the book, which is filled with industry-tested tips and tricks, you will have mastery over series forecasting and will have acquired enough skills to tackle problems in the real world.
What you will learn

Learn how to manipulate and visualize series data like a pro
Set strong baselines with popular models like ARIMA
Discover how series forecasting can be cast as regression
Eeer features for machine learning models for forecasting
Explore the exciting world of ensembling and stacking models
Learn about the global forecasting paradigm
Understand and apply state-of-the-art deep learning models like N-BEATS, AutoFormer, and more
Discover multi-step forecasting and cross-validation strats

Who This Book Is For

The book is ideal for data scientists, data analysts, machine learning eeers, and python developers who want to build industry-ready series models. Since the book explains most concepts from the ground up, basic proficiency in python is all you need. A prior understanding of machine learning or forecasting would help speed up the learning. For seasoned practitioners in machine learning and forecasting, the book has a lot to offer in terms of advanced techniques and traversing the latest research frontiers in series forecasting.
Table of Contents

Introducing Series
Acquiring and Processing Series Data
Analyzing and Visualizing Series Data
Setting a Strong Baseline Forecast
Series Forecasting as Regression
Feature Eeering for Series Forecasting
Target Transformations for Series Forecasting
Forecasting Series with Machine Learning Models
Ensembling and Stacking
Global Forecasting Models
Introduction to Deep Learning
Building Blocks of Deep Learning for Series
Common Modelling Patterns for Series
Attention and Transformers for Series
Strats for Global Deep Learning Forecasting Models
Specialized Deep Learning Architectures for Forecasting
Multi-Step Forecasting
Evaluating Forecasts - Forecast Metrics
Evaluating Forecasts - Validation Strats



DOWNLOAD

https://1dl.net/qvfmq55085tz/GLaTc6mG_Modern_Time.rar.html