Forecasting methods are techniques used by manager of many different occupations. They use them to try and predict the outcome of the future. Managers are forced to make very important decisions that will greatly impact the success of their business. Some managers may form their decision based on previous sales or their own past experiences. Forecasting is a more reliable way for the managers to make their decisions, even though no method can provide a totally accurate prediction. There are a number of different mathematical methods that managers can use.
Three of the traditional forecasting methods are time series analysis, regression, and qualitative methods. (Taylor, 2007) The time series analysis is a category of statistical techniques that uses historical data to predict future behavior. This method assumes that what happened in the past will happen again in the future. So the only factor that this method relates to is time. The time series methods are very useful for short- and medium-range forecasting, but can also be used to long-range forecasting.
Time series techniques relate a single variable being forecast to time, in contrast regression methods attempt to develop a mathematical relationship between the item being forecast and factors that cause it to behave the way it does. Qualitative methods use management judgment, expertise, and options to make forecasts. They are generally easy to understand, simple to use, and not very costly. (Taylor, 2007) For solving the University Bookstore’s problem of knowing how many computers to stock I used the mean absolute deviation method.
MAD is the average, absolute difference between the forecast and the demand. It is also one of the most popular and simplest-to-use ways of measuring forecast error. That was one reason that I chose this method, I also chose it because it had the lowest forecast error. I used the exponential smoothing of a = . 5 for computing my forecast. I chose . 5 because the closer a is to 0 the forecast will react and adjust more slowly to the differences between the actual demand and the forecasted demand.
And the higher a is, the more sensitive the forecast will be to changes in the recent demand. The most commonly used values for a range between . 01 and . 50. The forecast error that I computed by using the MAD method is 49. 13. When I first came up with this number I thought that it was high until I saw the errors from the other forecast methods. I also computed the demand using the 3- and 5-month moving averages. The results that I computed from both averages were really far off from the actually demand.
They both were much lower than the demand. Being that the manager at the bookstore has a very important decision to make in determining how many computers to stock, it is also very important for him to use the most accurate as possible forecasting method. His decision not only affects the computer sales, it also affects the amount of storage space that the bookstore will have for other items and the number of staff that needs to be hired. If I were the manager at the bookstore, I would feel safe in my decision of using the MAD method.
I also would compute the forecast error for the other high items as well. Although forecast methods cannot provide a totally accurate prediction for the future, it can provide a good guideline for making a decision. Forecasting methods have a good track record of performance for many companies that have used them. For these reasons, I feel that the MAD method is the best chose for the University Bookstore.
Taylor III, B. W. (2007). Quantitative Methods (4th Custom ed). Upper Saddle River, NJ: Prentice Hall