Chapter 5: Time Series and Forecasting

Stacks of coins in front of a computer screen with a green arrow rising from left to right. — **Figure 5.1** Time series analysis involves the examination of data points collected at specific time intervals; it is crucial for identifying trends and patterns that inform predictions and strategic decisions.Time series analysis involves the examination of data points collected at specific time intervals; it is crucial for identifying trends and patterns that inform predictions and strategic decisions. (credit: modification of work "Bitcoin steigend" by Tim Reckmann/Flickr, CC BY 2.0)

The future can be very unpredictable. Wouldn’t it be wonderful to know whether a given stock price will rise or fall in value over the next year, which baseball team will win the next World Series, or if it might rain on the particular day that you happen to be planning to go to the beach? A manufacturer may want to know how the demand for their products changes over time. Politicians would like to know how high their favorability with voters will be on election day. While we cannot see the future, there may be patterns that point to certain outcomes as being more likely than others. In this chapter we explore the concept of time series and develop the necessary tools to discover trends and repeating patterns hidden within time series data to forecast future values of the series and quantify the uncertainty of those predictions.

Adapted from Principles of Data Science by OpenStax (openstax.org), licensed under CC BY-NC-SA 4.0. Changes were made. License: CC-BY-NC-SA-4.0.