If sales value in Jan 2017 as the sale value of forecast in Jan 2018 then what method need to use? 1. Average 2. Seasonal naïve 3. Drift 4. naïve 5. random.
Answer: 2. Seasonal naïve
Explanation:
Various Forecasting Method:
1. No, Average: The forecasts of all future values are equal to the "average" of the historical data.
This method can not be applied as same value is taken or future forecast not the average.
2. Yes, Seasonal naïve: In this method, each forecast is set to be equal to the last observed value of forecast from the same season of the year. Like the above question the same month of the previous year( Data of Jan 2017 is used for the forecast of Jan 2018) .
This method is useful for seasonal data. In this approach, time series is believed to have seasonality, hence this method is more appropriate where the forecasts are equal to the value from last season.
3. No, Drift: A variation of the naïve method where increase or decrease of forecasts over time is allowed according to the amount of change over time (known as drift) is set to be the average changes seen in the historical data.
4. No, naïve: This is somewhat random. In this method,each forecast is set to be equal to the value of the last observation.
5. No, Random : Random methods is new approach for forecasts in high-dimension. Forecasts are taken by averaging over forecasts from many sub model of random selection.
Get Answers For Free
Most questions answered within 1 hours.