please rewrite and do by tomorrow
Running Head: ALTERNATIVE FUEL COMPANY 0
Alternative Fuel Company
BUS632 Advanced Logistics
Alternative Fuel Company
Demand forecasting is a vital component of any successful organization that sells goods or provides a service. Supply chain planning today starts with some form of forecasting. Coordinating supply and demand is at the heart of operational planning. This is because most, if not all, production systems cannot automatically respond to market demand instantaneously. Therefore some estimate or forecast is necessary to keep production efficient and effective (Blocher, Mabert, Soni, & Venkataramanan, 2004).
Over the next few pages the discussion will involve forecast analysis and which forecast models are better suited for different situations. The best way to achieve this is to provide an example of certain situations and analyze which models are better suited and why. The company that will be used to help analyze those situations is the Alternative Fuel Company.
The Alternative Fuel Company is a relatively new company that is now in its fourth year of business. In its first year of business the company forecasted 1000 units would be needed to satisfy demand. The forecast model used in their first year of business would have to be judgmental forecasting. This is due to the lack of historical data from a start-up company. Judgmental forecasting uses judgment or intuition to help forecast demand. This model also uses surveys, questionnaires, and customer feedback to forecast (Murphy & Wood, 2011). With no previous year’s data the only real option for forecasting, initially, is judgmental forecasting.
Judgmental forecasting is a more qualitative forecasting method who’s target is to bring together in a sensible, unbiased, and precise way all the data and judgments that are related to the demand being assessed. This technique is used frequently in new-technology territory where the launch of a new product or service may need new ways of thinking or innovation. This is especially true when supply and demand are hard to estimate and market penetration is uncertain (Chambers, Mullick, & Smith, 2001).
The Alternative Fuel Company’s first year in business saw it sell 800 units. This was not far from 1000 the company forecasted using judgmental forecasting. Now, however, the company is in its fourth year of business and has three years of data to use for future forecasts. According to table 1, below, the company has seen improved sales over their existence.
Year | Units |
800 | |
1200 | |
2000 |
Table 1. Sales for the first three years of the Alternative Fuel Company
With three years of data to use the company can use a more quantitative method of forecasting. The preferred forecasting method to use with some historical data available is time series forecasting. This model of forecasting is dependent on past demand (Murphy & Wood, 2011). It takes a weighted approach to forecasting using historical data. In the case of the Alternative Fuel Company a simple moving average can be used to help forecast. This forecast technique simply uses an average from each year to forecast for following year as seen in table 2, below.
Year | Units | SimpleMA | Projected Demand |
800 | .333 | 266 | |
1200 | .333 | 400 | |
2000 | .333 | 666 | |
--- | --- | 1332 |
The draw back to this technique is that it does not take into consideration the weight of the most current data. The simple moving average takes each year inconsideration, but does not add value to the most current data. This can cause issues with forecasting because the most current data reflects the most current trends. Using old data with the same weight as new data can skew any forecast. A better technique to use with historical data is a weighted moving average.
The technique of weighted moving averages will add more value to the most recent data and reduce value as the data becomes older. So, newer data has more relevance than older data. Taking a look at table 2, below, the weighted average for each year is multiplied by the units sold for each year. Then the total is derived from the sum of the weighted calculations. In this case the forecasted number of units for the fourth year is 1640 units. With the Alternative Fuel Company the better forecast will come from the weighted moving average.
Year | Units | Weighted MA | Projected Demand |
800 | 0.10 | 80 | |
1200 | 0.30 | 360 | |
2000 | 0.60 | 1200 | |
--- | --- | 1640 |
Table 2. Alternative Fuel Company weighted average for the fourth year.
The quantitative approach of time series forecasting needs historical data in order forecast accurately. One of the essential principles of forecasting when historical data is available is that data on previous performances can be used to gauge current rates of sales (Chambers, Mullick, & Smith, 2001). This approach can also help to determine how fast the rate of change is, which can be a very important factor when it comes to supply and customer satisfaction, which brings the discussion to cause and effect.
“Cause and effect forecasting assumes that one or more factors are related to demand and that the relationship between cause and effect can be used to estimate future demand” (Murphy & Wood, 2011, pg 114). With cause and effect there are two different types; multiple and simple regression. Multiple regression meaning that there are multiple factors influencing demand while simple regression has only one factor.
In the case of the Alternative Fuel Company a cause and effect approach can be used. The company has found out that a new luxury tax is being levied on all imports into China. The company expects that this will cause China sales to be reduced by half. Using the simple moving average from above (1332) combined with the simple regression cause & effect knowledge of a 50% decrease in sales, the forecasted demand for the fourth year should decrease by half as well. This would bring the demand to just under 700 units.
In conclusion the Alternative Fuel Company had to make some forecasting decisions regarding fuel sales. In the first year the company used judgmental forecasting because of a lack of historical data. The following years allowed for more data to be collected for future forecast using the time series model. Using this technique the company was able to use both a simple and weighted moving average to forecast demand for fuel. Finally a cause and effect technique was used to address a simple regression situation that added a luxury tax and, ultimately, decreased the demand for the fourth year.
There is no full proof forecasting method. The definition of forecast says that it is only a prediction or estimate of future events. This means looking into the future for a best guess, if you will. Technology has helped forecasting become less bulky and more scientific. However, there is still no technology that is totally capable of getting it 100% right (Murphy & Wood, 2011). Forecasting is a business necessity. This author predicts techniques will only get better.
Resources
Blocher, J. D., Mabert, V. A., Soni, A. K., & Venkataramanan, M. A. (2004). Forecasting; Including an Introduction to Forecasting using the SAP R/3 System. Retrieved from Indiana University Kelley School of Business website: https://kelley.iu.edu/mabert/e730/forecasting_february_2004.pdf
Chambers, J. C., Mullick, S. K., & Smith, D. D. (2001). How to Choose the Right Forecasting Technique. Retrieved from https://hbr.org/1971/07/how-to-choose-the-right-forecasting-technique
Murphy, P. R., & Wood, D. F. (2011). Contemporary logistics (10th ed.). Upper Saddle River, NJ: Prentice Hall.