Which forecasting model assigns greater weight to more recent values?

The model that assigns greater weight to more recent values is known as exponential smoothing. This forecasting technique is designed specifically to give more emphasis to the latest observations when predicting future values, which makes it particularly useful in scenarios where recent trends are more indicative of future outcomes.

Exponential smoothing involves applying a smoothing constant, which determines the weight given to the most recent observation relative to the previous forecast. As a result, when new data becomes available, it can adjust the forecast more significantly in response to recent changes, making it responsive to trends and fluctuations in the dataset.

In contrast, other models such as the moving average give equal weight to all values within the specified period, therefore failing to prioritize the most recent data. Causal models typically involve understanding the relationships between variables rather than focusing solely on historical data trends, while time series models may analyze past data without the specific weighting mechanism inherent in exponential smoothing.