Probability & Statistics

A time series model is a forecasting technique that attempts to predict the future values of a variable by using only historical data on that variable. There are many variables you can use, as long as you have values that are recorded at successive intervals of time. Here are some examples of variables you can use to forecast. 1. Select any dataset from any company in the retail market of your choice with a variable you would like to forecast. (area is highlighted in blue) 2. State the variable you are forecasting. 3. Select at least eight consecutive data values. 4. Using the Time Series Forecasting Templates, determine the following for the selected variable: moving average, weighted moving average, and exponential smoothing 5. Copy/paste the results of each method: address the following... the number of periods used in the moving average method. the weights used in the weighted moving average. the value of a used in exponential smoothing. 6. Indicate the "next period" prediction for each method. 7. Choose one of the following: Formulate a sentence that identifies the prediction. Circle, draw, etc. on the chart to indicate which value is the prediction for the next time period. 8. Suppose that the forecasting results are from three different branches of a company. Based on the MAD (mean absolute deviation) value, how would you prioritize the need to update the forecasting methods to improve overall predictions? Note: The higher the MAD value the worse the forecast. Indicate a rank of 1, 2, or 3 for each forecast with a 1 being the highest priority. 9. Provide a brief recommendation to the company concerning the order in which the forecasts should be completed including why they are ranked in that order