Microsoft Inc. is one of the corporations that have established themselves as global firms, functioning across different parts of the world. To develop a model for forecasting the company’s revenue over the years from 2012 to 2017, the following models would be used: Exponential moving average model, simple moving average, and the naïve method.
The simple moving average is considered as a mathematics moving average that is computed by tallying the new closing prices and dive up by the time duration numbers in the average calculation. In many cases, moving averages are often based on closing sales (Russell & Taylor, 2003). For example, in a five-year simple moving average, the total sales for the five years and closing sales which are then divided by 5. This portrays the moving average merely as an average that moves. This is because as shown in the excel spreadsheet, old information is dropped when new information is made available. This indicates the averages run with regard to the time scale. For example, from excel, the first years of the moving average sales are covering the final five years of the company’s sales. At the same time, the second year of the moving average leads to a drop in Microsoft’s first sales data of 25, 778 US dollars and continues to add new sale (Microsoft Inc., 2019). At the same time, in the third year of the moving average sales, there is a continued drop in the second year sales data, and the new sales are added as well. From the excel calculation, one will notice that the value of sales keeps increasing gradually over the years. It is much more comfortable and simple to use the simple moving average. But it is important to note that the moving average is often marginally below the value of the last sales that makes the moving average to lag behind.
The second model is the exponential moving average. This is a weighted moving average that offers more weighting, of significance, to the recent data price as compared to the simple moving average (Krajewski, Ritzman & Malhotra, 2014). EMA quickly responds to recent changes in price as compared to the SMA. To calculate the EMA, there are three stages involved. The first one is to calculate the SMA because an exponential moving average must start somewhere. The second steps entail the calculation of the multiplier for weighting the EMA, and lastly, calculating the current EMA.
For example, in the calculation, the 5-year period EMA used a third of the weighting in the most current sales value. As a result, the 5-year EMA can be regarded as a third of the EMA. But it is essential to note that weighing on a short term is much recommended as compared to weighing in the long term. Therefore, Microsoft’s 5-year period is relevant.
This is an estimation technique where the final period’s actuals are applied for forecasting with no attempt to adjust or establish the causal elements. It is used mostly for contrast with the forecast created by more refined approaches. It is relevant for a time series data since all estimates are presented as the value shown from the final observation. This means that the newest data provided by the operation’s set of data is treated as the forecast value for that period (Russell & Taylor, 2003). Thus, the last duration of Microsoft’s sales set of information is considered as the sales forecast for that given duration.
Based on the quantitative methods of forecasting above I would prefer using the EMA model. Even though it is complex as compared to the other two, it provides well-calculated forecast value that is accurate and feasible. At the same time, the EMA method reduces the lag witnessed in the simple moving average and calls for the use of shorter forecasting periods, consequently improving the levels of precision and accurateness.
Sales forecasting can, however, result in various results, causing either negative or positive financial metrics. Sales forecasting can enable the organization to meet the requirements and needs of consumers because they had earlier predicted and got prepared for the same. But, if the sales forecast is not accurately done, it can cause a lot of confusions leading customer dissatisfaction. In the end, the company can lose its competitive advantage and customer base thus resulting in reduced sales. This can cause significant harm to the company’s financial metrics and failure to achieve the anticipated sales volume.
Krajewski, L. J., Ritzman, L. P., & Malhotra, M. K. (2014). Operations management. Pearson,.
Mircosoft Inc. (2019) Microsoft’s revenue worldwide 2002-2018. Retrieved from https://www.statista.com/statistics/267805/microsofts-global-revenue-since-2002/
Russell, R. S., & Taylor, B. W. (2003). Operations management (Vol. 3). Upper Saddle River, NJ: Prentice Hall.