Time Series Decomposition

A raw time series, like the daily price of a stock, can be noisy and difficult to interpret. Time series decomposition is a statistical method that deconstructs a time series into several components, each representing one of the underlying categories of patterns.

Typically, we decompose a series into three parts:

• Trend: The long-term direction or movement of the data.
• Seasonality: Repeating patterns or cycles that occur at regular intervals (e.g., daily, weekly, yearly).
• Residuals (Noise): The random, irregular component left over after removing the trend and seasonality.