Quantitative Business Studies Department

Quantitative Business Studies Department

MGMT 660-02 Forecasting Assignment

Problem 1

Renewable Energy Co. Monthly Sales.xlsx

Renewable Energy Company sells devices which are capable of efficiently turning solar power into usable and efficient energy for consumers. They have provided the last five years of monthly sales figures and are looking to generate a forecasting technique which will project sales into the future with the minimum amount of error.

• Note – The first data point represents sales for the month of January in the first year.

1. Create a line plot to evaluate the properties of the monthly sales data. Provide a comment on the general properties of the sales data.
2. Create a 3-period moving average forecast (MA3).
3. Create an exponential forecast. Use a smoothing constant alpha = 0.2
4. Create a linear trend forecast.
5. Evaluate each of the forecasting techniques by comparing mean absolute error (MAE), the root- mean square error (RMSE), and the mean absolute percentage error (MAPE).
6. Provide a summary of your findings, to include an assessment of the best forecasting technique for this company.

Problem 2

Target Monthly Retail Sales.xlsx

Target is a large national retailer of consumer goods and is interested in determining the amount of seasonality within their retail sales. This information will allow the regional directors to evaluate the need for additional staffing during peak seasons. They have provided the past seventeen years of monthly retail sales.

1. Create a line plot to evaluate the properties of the historical monthly total retail sales data.
2. Calculate a 12-month moving average (MA-12) of the historical sales data and center if necessary.
3. Calculate the seasonal factor ratios.
4. Calculate the seasonal indices. If necessary, normalize seasonal indices.
5. Calculate the center moving average trend and generate a linear trend equation from the CMAT data.
6. Calculate and plot the cyclic factors.
7. Use the model to generate a forecast for each historical period.
8. Calculate the MAE, RMSE, and MAPE for the model.
9. Discuss your results. Do you notice any problems with your forecast model’s ability to track changes (in particular, the most recent months)? How did the model perform?

All submissions are to be uploaded through Brightspace. Each submission should include a Word document and/or Excel spreadsheet with all work.

Bibliography

Chase, C., & Wiley Online Library. (2013). Demand-driven forecasting a structured approach to forecasting (2nd ed., Wiley and SAS business series). Hoboken, N.J.: Wiley.

Evans, M. (2002). Practical business forecasting. Malden, MA