지수 평활법(Exponential smoothing)
2024. 12. 24. 19:25ㆍdata 공부/데이터전처리
single exponential smoothing
future expected value = past real value * a + past predicted value * (1-a)
- Forecasting Formula:
- Ft+1F_{t+1}: Forecast for the next period.
- XtX_t: Actual value at time tt.
- FtF_t: Forecast value at time tt.
- α\alpha: Smoothing constant (0 ≤ α\alpha ≤ 1).
- Smoothing Constant (α\alpha):
- Determines the weight of recent observations versus older ones.
- A higher α\alpha (closer to 1) gives more weight to recent data, making the model more responsive to changes.
- A lower α\alpha (closer to 0) gives more weight to older data, resulting in a smoother forecast.
- Initialization:
- The initial forecast (F1F_1) can be set to the first data point (X1X_1) or the average of the first few observations.
- Exponential Decay:
- The method assigns exponentially decreasing weights to past observations, ensuring that recent observations influence the forecast more than older ones.
Excel usage
= FORECAST.ETS(target_data, values, timeline, seasonal period, null data management, repeated timeline management)
'data 공부 > 데이터전처리' 카테고리의 다른 글
Decision tree Classifier (0) | 2024.12.24 |
---|---|
엑셀 대시보드 만들기 (0) | 2024.12.23 |
KNN (K-Nearest Neighbors) 알고리즘 (0) | 2024.12.20 |
Logistic Regression (1) | 2024.12.19 |
리니어 리그레션 및 예측 (1) | 2024.12.19 |