Data Mining For Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel® with XLMiner®, Second Edition

Chapter 15. Handling Time Series

In this chapter we describe the context of business time series forecasting and introduce the main approaches that are detailed in the next chapters (in particular, regression-based forecasting and smoothing-based methods). Our focus is on forecasting future values of a single time series. We discuss the difference between the predictive nature of time series forecasting versus the descriptive or explanatory task of time series analysis. A general discussion of combining forecasting methods or results for added precision follows. Next, we present a time series in terms of four components (level, trend, seasonality, and noise) and present methods for visualizing the different components and for exploring time series data. We close with a discussion of data partitioning (to create training and validation sets), which is performed differently than cross-sectional data partitioning.

Introduction

Time series forecasting is performed in nearly every organization that works with quantifiable data. Retail stores use it to forecast sales. Energy companies use it to forecast reserves, production, demand, and prices. Educational institutions use it to forecast enrollment. Governments use it to forecast tax receipts and spending. International financial organizations such as the World Bank and International Monetary Fund use it to forecast inflation and economic activity. Transportation companies use time series forecasting to forecast future travel. Banks and ...