A data analyst is tasked with forecasting quarterly sales for the upcoming year based on the last five years of sales data. Which of the following methods is most suitable for capturing seasonality and trend patterns in this analysis?

The ARIMA (AutoRegressive Integrated Moving Average) model with seasonality, also known as SARIMA (Seasonal ARIMA), is ideal for time series forecasting that includes both trend and seasonality components. ARIMA accounts for non-stationary trends and adjusts to periodic changes in data, making it suitable for capturing seasonal effects in quarterly sales data. By incorporating both autoregressive and moving average components with seasonality parameters, SARIMA can produce accurate forecasts for time-dependent patterns, which is essential in cyclical data like quarterly sales. The other options are incorrect because: • Option 1 (Linear Regression) lacks the ability to model seasonality directly. • Option 2 (Moving Average) smooths data but may not capture complex seasonality. • Option 3 (Exponential Smoothing) handles trends but not explicit seasonal effects. • Option 5 (K-Nearest Neighbors) is a non-parametric method and does not account for time series patterns.