Practical Time Series Forecasting with R: A Hands-On Guide, Second Edition provides an applied approach to time-series forecasting. Forecasting is an essential component of predictive analytics. The book introduces popular forecasting methods and approaches used in a variety of business applications. The book offers clear explanations, practical examples, and end-of-chapter exercises and cases. Readers will learn to use forecasting methods using the free open-source R software to develop effective forecasting solutions that extract business value from time-series data. Featuring improved organization and new material, the Second Edition also includes: - Popular forecasting methods including smoothing algorithms, regression models, and neural networks - A practical approach to evaluating the performance of forecasting solutions - A business-analytics exposition focused on linking time-series forecasting to business goals - Guided cases for integrating the acquired knowledge using real data* End-of-chapter problems to facilitate active learning - A companion site with data sets, R code, learning resources, and instructor materials (solutions to exercises, case studies) - Globally-available textbook, available in both softcover and Kindle formats Practical Time Series Forecasting with R: A Hands-On Guide, Second Edition is the perfect textbook for upper-undergraduate, graduate and MBA-level courses as well as professional programs in data science and business analytics. The book is also designed for practitioners in the fields of operations research, supply chain management, marketing, economics, finance and management. For more information, visit forecastingbook.com

We distinguish between three different ways of using real-time data to estimate forecasting equations and argue that the most frequently used approach should generally be avoided. The point is illustrated with a model that uses monthly observations of industrial production, employment, and retail sales to predict real GDP growth. When the model is estimated using our preferred method, its out-of-sample forecasting performance is clearly superior to that obtained using conventional estimation, and compares favorably with that of the Blue-Chip consensus.