An e-commerce company wants to understand the trend of holiday season sales over the past decade to forecast future sales. Which analysis method should the data analyst employ to make reliable predictions?

The moving average time series method is ideal for analyzing and forecasting seasonal sales trends as it smooths out short-term fluctuations and highlights long-term trends. In e-commerce, where seasonal variations such as holiday sales significantly impact revenue, the moving average allows analysts to account for cyclical patterns, making it a strong tool for forecasting. By averaging data over specified intervals, it reduces noise and captures the overall sales trend, helping the company estimate future sales based on historical holiday trends. Moving average time series thus provides an accessible and reliable framework for sales trend analysis, directly aligned with the company’s forecasting needs. The other options are incorrect because: • Cross-sectional Analysis analyzes data at a single point in time, unsuitable for trend forecasting. • Linear Regression does not account for seasonality or time-based variations, limiting its application. • Hierarchical Clustering groups data rather than identifies patterns over time. • Random Forest can be used for predictions but is not designed for time-based trend analysis.