Nowadays, a variety of forecasting methods are used by different organizations. In actuality, it is hardly possible to speak about the most efficient or less efficient. Nonetheless, it should be pointed out that among the variety of methods there are some which are widely spread but are still not deprived of certain drawbacks as well as advantages. At the same time, it is necessary to realize that regardless their advantages or drawbacks forecasting methods are essential and practically each method is unique though some common features may be traced as well.
Time series methods
Among the most popular forecasting methods, it is possible to single out the group of methods that are traditionally referred to as time series methods. Basically, these methods attempt to understand time series, often to understand the underlying theory of the data points, or what is particularly important to make forecasts.
Traditionally, time series prediction is “the use of a model to predict future events based on known past events: to predict future data points before they are measured” (Geisser 1993). Often the standard example is the opening price of a share of stock based on its past performance. At the same time, there are different methods within time series, such as Moving Average, Exponential Smoothing, and Trend Estimation.
One of the methods used for forecasting is Moving Average. This method is widely spread in finance and is very important in prediction future development of the situation in financial market. It should be pointed out that this method is rather universal and similar to other methods that can be calculated for any time series. However, it is mainly applied to stock prices, returns or trading volumes. It should be also pointed out that this method may be used equally for short-term and long-term forecasts, and the parameters of the moving average will be set accordingly. A typical example of simple Moving Average may be presented as follows: a 10-day simple moving average of closing price is the outweighed mean of the previous n data points, for instance, the previous 10 days closing prices. If those prices are p1 and p2 then the formula is: SMA=p1+p2+…+pn/n
Another method is Exponential Smoothing. This method may be briefly characterized as a way of “estimating the next value of sequence of observations” (Geisser 1993). Traditionally, this method is used only for non-seasonal time series showing no systemic trend. This characteristic makes this method totally different from the previous one which may be used for both short-term and long-term forecasting without any seasonal limits. At the same time, Exponential Smoothing similarly to Moving Average is also based on past observations which are used as a basis for forecasting the future perspective and trends. This method traditionally considers natural to take as an estimate of xn+1 a weighted some of the past observations. It is worthy of note that it also seems “sensible to give more weight to recent observations and less weight to observations further back in the past” (Armstrong 2001:201).
Finally, there is one more method that will be discussed in terms of this paper – Trend Estimation. Unlike both previous methods, Trend Estimation does not simply forecast the possible changes but it basically focuses on the trends that will be typical in the future that can help better understand the future development of the situation at large. Traditionally, Trend Estimation is defined as “the application of statistical techniques to make and justify statements about trends in the date” (Kress and Snyder 1994:175).
It should be pointed out that past observations are also important for this method but it is not less important to analyze the current situation and attempt to trace possible changes and in such a way forecast future trends. In such a way, this method is based on a thorough analysis of the past and present observations that contribute to the better understanding of possible changes and future trends.
The practical application of Trend Estimation
Obviously to properly assess the efficiency of any method of forecasting, it is necessary to practically apply it. Speaking about our organization, it is necessary to point out that basically trend estimation is widely used since this method has proved its high efficiency in forecasting demand under conditions of uncertainty. In fact, on using this method, it is necessary to take into consideration the past observations and recent ones and properly assess them. On the basis of this assessment it is possible to make a plausible forecast about their future development. As a result, the forecast is developed in its general form.
Furthermore, on assessing the situation in general, it is possible to start to build up basic trends that would be the characteristics of the future. Consequently, it is possible to build a particular strategy for a particular aspect of the organizational functioning. For instance, forecasting the trends in demand’s changes. This is why it is possible to make a forecast of main trends even in the conditions of uncertainty. On the other hand, it is necessary to realize that this method does not provide ample opportunities to forecast precisely the development of the situation. Nonetheless, the revealing of the main trends helps to undertake essential steps to change the development of the situation for better.
Thus, taking into consideration all above mentioned, it is possible to conclude that there are different methods that can be applied for forecasting. Among the most popular may be named Moving Average, Exponential Smoothing, and Trend Estimation. To a significant extent they are different but at the same time there are a lot of common features that may be found between these methods. Also it is worthy of note that they may be characterized by different efficiency but, nonetheless, there is no ideal method that could be perfect and forecast the future development of the situation much more precisely than any other. This is why it is necessary to recommend to apply a variety of methods of forecasting in order to properly assess the perspectives and possible changes that can occur in the functioning of an organization, in the market, etc. In other words, it is necessary to use a complex of methods in order to achieve possibly higher efficiency of forecasting.
Armstrong, J. Scott (ed.) (2001). Principles of forecasting: a handbook for researchers and practitioners. Norwell, Massachusetts: Kluwer Academic Publishers.
Kress, George J. and Snyder, John (1994). Forecasting and market analysis techniques: a practical approach. Westport, Connecticut, London: Quorum Books.
Geisser, Seymour. (1993). Predictive Inference: An Introduction. Chapman & Hall, CRC Press.
NOTE: You’ve tried to find relevant case studies online for free, but only got more disappointed and frustrated? Don’t risk the originality of your paper using those online samples, and fill out an order form at EssayLib.com to get case study writing help at an affordable price. Full confidentiality and Money Back guarantee back up your choice.