Time Series for Data Science: Analysis and Forecasting

Data Science students and practitioners want to find a forecast that  “works” and don’t want to be constrained to a single forecasting  strategy, Time Series for Data Science: Analysis and Forecasting  discusses techniques of ensemble modelling for combining information  from several strategies. Covering time series regression models,  exponential smoothing, Holt-Winters forecasting, and Neural Networks. It  places a particular emphasis on classical ARMA and ARIMA models that is  often lacking from other textbooks on the subject.

This book is  an accessible guide that doesn’t require a background in calculus to be  engaging but does not shy away from deeper explanations of the  techniques discussed.

Features:
Provides a thorough coverage  and comparison of a wide array of time series models and methods:  Exponential Smoothing, Holt Winters, ARMA and ARIMA, deep learning  models including RNNs, LSTMs, GRUs, and ensemble models composed of  combinations of these models.Introduces the factor table representation  of ARMA and ARIMA models. This representation is not available in any  other book at this level and is extremely useful in both practice and  pedagogy.Uses real world examples that can be readily found via web  links from sources such as the US Bureau of Statistics, Department of  Transportation and the World Bank.There is an accompanying R package  that is easy to use and requires little or no previous R experience. The  package implements the wide variety of models and methods presented in  the book and has tremendous pedagogical use.