Performing smoothing – exponential smoothing

Another commonly used smoothing technique is exponential smoothing. It gives more weight to recent observations and less to the older ones. While moving average smoothing applies equal weights to past observations, exponential smoothing applies exponentially decreasing weights to observations as they get older. A major advantage it has over the moving average is the ability to capture sudden changes in the data more effectively. This is because exponential smoothing gives more weight to recent observations and less to previous ones, unlike the moving average, which applies equal weights.

Beyond time series exploratory analysis, both moving average and exponential smoothing techniques can also be used as a basis for forecasting future values in a time series.

We will explore the exponential smoothing technique in Python. We will use the ExponentialSmoothing module in statsmodels.

Getting ready

We will work with one dataset...