Time series analysis

In this lesson

1. 0:00 Time series analysis introduction
2. 2:21 Calculating moving averages worked example
3. 4:47 Additive model forecasting method
4. 5:55 Multiplicative model forecasting method
5. 6:40 Limitations of time series models

About this lesson

This is essential for the Performance Management and Advanced Performance Management papers, where you'll need to analyse patterns in sales, costs, and other business metrics over time. You'll discover what makes up a time series—the underlying trend, seasonal variations that repeat within a year, cyclical patterns, and random fluctuations—and why organisations separate these to plan effectively. The lesson walks you through calculating moving averages to smooth out noise in the data, then shows you how to apply two forecasting approaches: the additive model (where components are added together) and the multiplicative model (where they're multiplied). You'll work through practical examples forecasting sales using trend lines and seasonal adjustments. The lesson also covers the limitations of time series analysis. Moving averages work well for identifying patterns, but the models assume the past reliably predicts the future—which isn't always true if customer behaviour, market conditions, or data quality have changed. You'll learn to think critically about when these forecasts are reliable and what other factors organisations should consider alongside time series projections.

Duration: 7m