FORECASTING CONCEPTS & TECHNIQUES

Productions and Operations Project

INTRODUCTION
Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. Eg:- A commonplace example might be estimation for some variable of interest at some specified future date. It makes use of formal statistical methods by employing time series, crosssectional or longitudinal data, or alternatively to less formal judgmental methods. In any case, the data must be up to date in order for the forecast to be as accurate as possible. Usage can differ between areas of application: for example in hydrology, the terms "forecast" and "forecasting" are sometimes reserved for estimates of values at certain specific future times. Risk and uncertainty are central to forecasting. It is generally considered good practice to indicate the degree of uncertainty attaching to forecasts. Good forecasts can lead to Reduced inventory costs Lower overall personnel costs Increased customer satisfaction

Some common examples of forecasting are

Manufacturing firms forecast demand for their product, to schedule manpower and raw material allocation. Service organizations forecast customer arrival patterns to maintain adequate customer service Security analysts forecast revenues, profits, and debt ratios, to make investment recommendations Firms consider economic forecasts of indicators (housing starts, changes in gross national profit) before deciding on capital investments.

SOME COMMON APPLICATIONS OF FORECASTING

The process of climate change and increasing energy prices has led to the usage of Egain Forecasting of buildings. The method uses Forecasting to reduce the energy needed to heat the building, thus reducing the emission of greenhouse gases. Forecasting is used in the practice of Customer Demand Planning in every day business forecasting for manufacturing companies. Forecasting has also been used to predict the development of conflict situations. Experts in forecasting perform research that use empirical results to gauge the effectiveness of certain forecasting models. Research has shown that there is little difference between the accuracy of forecasts performed by experts knowledgeable of the conflict situation of interest and that performed by individuals who knew much less. The discipline of demand planning, also sometimes referred to as supply chain forecasting, embraces both statistical forecasting and a consensus process. - Forecasting can be used in Supply Chain Management to make sure that the right product is at the right place at the right time. Accurate forecasting will help retailers reduce excess inventory and therefore increase profit margin. Studies have shown that extrapolations are the least accurate, while company earnings forecasts are the most reliable. Accurate forecasting will also help them meet consumer demand.

SOME OTHER APPLICATIONS OF FORECASTING Forecasting has application in these situations also:

Weather forecasting, Flood forecasting and Meteorology Transport planning and Transportation forecasting Economic forecasting Technology forecasting Earthquake prediction

Land use forecasting Product forecasting Player and team performance in sports Telecommunications forecasting Political Forecasting Sales Forecasting

LIMITATIONS
1). Human Limitations Employees who do not cooperate across departments or employees with strong opinions can skew the results. If the sales force receives incentives for beating projections, they may even provide low numbers to improve their chances for rewards. Buyer surveys produce wrong information if customers tell sellers what they want to hear. For example, sometimes buyers say they will purchase a certain quantity but do not follow up with purchases. 2). Limitations of Economic Predictions Quantitative forecasting uses past numbers as its basis. This type of forecasting normally includes the effects of the leading indicator series and other complex economic data. The leading indicator series includes information on stock prices, unemployment insurance claims and the money supply. Although forecasting that uses such data is highly mathematical, it makes a crucial assumption that history predicts the future. If market conditions change unexpectedly, these methods become less accurate. 3). Not Enough Data The accuracy of a forecast depends on the quality of the data used as a basis for the financial models and projections. A company entering a new market space does not have any historical data on which to base the projections. Startup companies find it extremely difficult to predict how quickly their revenues will grow.

4). As proposed by Edward Lorenz in 1963, long range weather forecasts, those made at a range of two weeks or more, are impossible to definitively predict the state of the atmosphere, owing to the chaotic nature of the fluid dynamics equations involved. Extremely small errors in the initial input, such as temperatures and winds, within numerical models double every five days.

CATEGORIES OF FORECASTING METHODS

Qualitative forecasting techniques are subjective, based on the opinion and judgment of consumers, experts; appropriate when past data is not available. It is usually applied to intermediate-long range decisions.

They are: A). Delphi method - The Delphi method is a structured

communication technique, originally developed as a systematic, interactive forecasting method which relies on a panel of experts. In the standard version, the experts answer questionnaires in two or more rounds. After each round, a facilitator provides an anonymous summary of the experts forecasts from the previous round as well as the reasons they provided for their judgments. Thus, experts are encouraged to revise their earlier answers in light of the replies of other members of their panel. It is believed that during this process the range of the answers will decrease and the group will converge towards the "correct" answer. Finally, the process is stopped after a pre-defined stop criterion (e.g. number of rounds, achievement of consensus, stability of results) and the mean or median scores of the final rounds determine the results. Other versions, such as the Policy Delphi, have been designed for normative and explorative use, particularly in the area of social policy and public health. In Europe, more recent web-based experiments have used the Delphi method as a communication technique for interactive decision-making and edemocracy. Delphi is based on the principle that forecasts (or decisions) from a structured group of individuals are more accurate than those from unstructured groups. This has been indicated with the term "collective intelligence". The technique can also be adapted for use in face-to-face meetings, and is then called mini-Delphi or Estimate-Talk-Estimate (ETE). Delphi has been widely used for business forecasting and has certain advantages over another structured forecasting approach, prediction markets.

B). Market research - Market research is any organized effort to

gather information about markets or customers. It is a very important component of business strategy. The term is commonly interchanged with marketing research; however, expert practitioners may wish to draw a distinction, in that marketing research is concerned specifically about marketing processes, while market research is concerned specifically with markets. Market research is a key factor to get advantage over competitors. Market research provides important information to identify and analyze the market need, market size and competition. Market research, includes social and opinion research and is the systematic gathering and interpretation of information about individuals or organizations using statistical and analytical methods and techniques of the applied social sciences to gain insight or support decision making.

C). Grass root - The Grassroots technique is based on the concept of

asking those who are close to the eventual consumer, such as salespeople, about what they are going to sell next period, and added the forecasts to predict total demand. It requires an experienced stable work force that knows the customer base. It is not good at retail, can be expensive, takes sales people away from sales effort and results can be biased. In more sophisticated systems, forecasts may be adjusted on the basis of the historical correlation between the salespersons forecasts and the actual sales.

D). Panel consensus This technique is based on the assumption that several minds are better than one. Groups of people who can give sensible estimates of sales, such as sales representatives and brand managers, discuss sales expectations and arrive at some consensus on which to base the forecast. When using Panel Consensus forecasting, one should bear in mind that social pressure, peer pressure and emotional attitudes displayed in small group behaviour can effect the results of the forecast. Furthermore, research suggests that groups are less risk-averse than their component members.

E). Historical analogy - Similar products and markets often display

similar growth patterns or life cycles on which one can base its forecast. The

S-shaped product life cycle is a typical example. It is generally divided into four stages:

Introduction - a period of slow growth while the product is introduced onto the market.

Growth - sales rapidly increase at an increasing growth rate as the market accepts the product.

Maturity - sales increase slowly but with a decreasing growth rate. The product has now been accepted by the majority of the people that are likely to buy it.

Decline - a decline in sales caused by changes in tastes, increased competition or a shift away from your product towards a new or improved product.

QUANTITATIVE METHODS OF FORECASTING

Quantitative forecasting models are used to estimate future demands as a function of past data; appropriate when past data is available. It is usually applied to short-intermediate range decisions. They are:

Arithmetic Average Simple Moving Average (N-Period) Weighted Moving Average (N-period) Simple Exponential Smoothing

A). ARITHMETIC AVERAGE

In mathematics and statistics, the arithmetic mean, or simply the mean or average when the context is clear, is the central tendency of a collection of numbers taken as the sum of the numbers divided by the size of

the collection. The collection is often the sample space of an experiment. The term "arithmetic mean" is preferred in mathematics and statistics because it helps distinguish it from other means such as the geometric and harmonic mean. In addition to mathematics and statistics, the arithmetic mean is used frequently in fields such as economics, sociology, and history, though it is used in almost every academic field to some extent. For example, per capita GDP gives an approximation of the arithmetic average income of a nation's population. Suppose we have sample space defined via the equation . Then the arithmetic mean is

. If the list is a statistical population, then the mean of that population is called a population mean. If the list is a statistical sample, we call the resulting statistic a sample mean. The arithmetic mean of a variable is often denoted by a bar, for example (read "x bar") would be the mean of some sample space .

B). SIMPLE MOVING AVERAGE

Intuitively, the simplest way to smooth a time series is to calculate a simple, or unweighted, moving average. The smoothed statistic st is then just the mean of the last k observations:

where the choice of an integer k > 1 is arbitrary. A small value of k will have less of a smoothing effect and be more responsive to recent changes in the data, while a larger k will have a greater smoothing effect, and produce a more pronounced lag in the smoothed sequence. One disadvantage of this technique is that it cannot be used on the first k 1 terms of the time series.

C). WEIGHTED MOVING AVERAGE

A slightly more intricate method for smoothing a raw time series {xt} is to calculate a weighted moving average by first choosing a set of weighting factors

such that

and then using these weights to calculate the smoothed statistics {st}:

In practice the weighting factors are often chosen to give more weight to the most recent terms in the time series and less weight to older data. This technique has the same disadvantage as the simple moving average technique (i.e., it cannot be used until at least k observations have been made), and that it entails a more complicated calculation at each step of the smoothing procedure. In addition to this disadvantage, if the data from each stage of the averaging is not available for analysis, it may be difficult if not impossible to reconstruct a changing signal accurately (because older samples may be given less weight). If the number of stages missed is known however, the weighting of values in the average can be adjusted to give equal weight to all missed samples to avoid this issue.

The graph shows how the weights decrease, from highest weight for the most recent data points, down to zero.

D). SIMPLE EXPONENTIAL SMOOTHING

Exponential smoothing was first suggested by Charles C. Holt in 1957, although the formulation below, which is the one commonly used, is attributed to Brown and is known as "Brown's simple exponential smoothing". The simplest form of exponential smoothing is given by the formulae:

where is the smoothing factor, and 0 < < 1. In other words, the smoothed statistic st is a simple weighted average of the previous observation xt-1 and the previous smoothed statistic st1. The term smoothing factor applied to here is something of a misnomer, as larger values of actually reduce the level of smoothing, and in the limiting case with = 1 the output series is just the same as the original series (with lag of one time unit). Simple exponential smoothing is easily applied, and it produces a smoothed statistic as soon as two observations are available. Values of close to one have less of a smoothing effect and give greater weight to recent changes in the data, while values of closer to zero have a greater smoothing effect and are less responsive to recent changes. There is no formally correct procedure for choosing . Sometimes the statistician's judgment is used to choose an appropriate factor. Alternatively, a statistical technique may be used to optimizethe value of . For example, the method of least squares might be used to determine the value of for which the sum of the quantities (sn-1 xn-1)2 is minimized. Unlike some other smoothing methods, this technique does not require any minimum number of observations to be made before it begins to produce results. In practice, however, a "good average" will not be achieved until several samples have been averaged together; for example, a constant signal will take approximately 3/ stages to reach 95% of the actual value. To accurately reconstruct the original signal without information loss all stages of the exponential moving average must also be available, because older samples decay in weight exponentially. This is in contrast to a simple moving average, in which some samples can be skipped without as much loss of information due to the constant weighting of samples within the average. If a known number of samples will be missed, one can adjust a weighted average for this as well, by giving equal weight to the new sample and all those to be skipped. This simple form of exponential smoothing is also known as an exponentially weighted moving average (EWMA)

IT IS CALLED EXPONONTIAL BECAUSE :By direct substitution of the defining equation for simple exponential smoothing back into itself we find that

In other words, as time passes the smoothed statistic st becomes the weighted average of a greater and greater number of the past observations xtn, and the weights assigned to previous observations are in general proportional to the terms of the geometric progression {1, (1 ), (1 )2, (1 )3, }. A geometric progression is the discrete version of an exponential function, so this is where the name for this smoothing method originated. Exponential smoothing is a technique that can be applied to time series data, either to produce smoothed data for presentation, or to make forecasts. The time series data themselves are a sequence of observations. The observed phenomenon may be an essentially random process, or it may be an orderly, but noisy, process. Whereas in the simple moving average the past observations are weighted equally, exponential smoothing assigns exponentially decreasing weights over time. Exponential smoothing is commonly applied to financial market and economic data, but it can be used with any discrete set of repeated measurements. The raw data sequence is often represented by {xt}, and the output of the exponential smoothing algorithm is commonly written as {st}, which may be regarded as a best estimate of what the next value of x will be. When the sequence of observations begins at time t = 0, the simplest form of exponential smoothing is given by the formulas

where is the smoothing factor, and 0 < < 1.

FORECAST ERROR
A forecast error is the difference between the actual or real and the predicted or forecast value of a time series or any other phenomenon of interest. In simple cases, a forecast is compared with an outcome at a single timepoint and a summary of forecast errors is constructed over a collection of such time-points. Here the forecast may be assessed using the difference or using a proportional error. By convention, the error is defined using the value of the outcome minus the value of the forecast.

In other cases, a forecast may consist of predicted values over a number of lead-times; in this case an assessment of forecast error may need to consider more general ways of assessing the match between the timeprofiles of the forecast and the outcome. If a main application of the forecast is to predict when certain thresholds will be crossed, one possible way of assessing the forecast is to use the timing-errorthe difference in time between when the outcome crosses the threshold and when the forecast does so. When there is interest in the maximum value being reached, assessment of forecasts can be done using any of: the difference of times of the peaks; the difference in the peak values in the forecast and outcome; the difference between the peak value of the outcome and the value forecast for that time point.

Forecast error can be a calendar forecast error or a cross-sectional forecast error, when we want to summarize the forecast error over a group of units. If we observe the average forecast error for a time-series of forecasts for the same product or phenomenon, then we call this a calendar forecast error or time-series forecast error. If we observe this for multiple products for the same period, then this is a cross-sectional performance error. Reference class forecasting has been developed to reduce forecast error. Combining forecasts has also been shown to reduce forecast error.

MEAN ABSOLUTE DEVIATION

In statistics, the absolute deviation of an element of a data set is the absolute difference between that element and a given point. Typically the point from which the deviation is measured is a measure of central tendency, most often the median or sometimes the mean of the data set. where Di is the absolute deviation, xi is the data element and m(X) is the chosen measure of central tendency of the data set sometimes the mean ( ), but most often the median.

The mean absolute deviation (MAD), also referred to

as the mean deviation, is the mean of the absolute deviations of a set of

data about the datas mean. In other words, it is the average distance of the data set from its mean during certain number of time periods. The equation for MAD is as follows: MAD = 1/n (|ei|) , where ei = Fi - Di This method forecast accuracy is very closely related to the mean squared error (MSE) method which is just the average squared error of the forecasts. Although these methods are very closely related MAD is more commonly used because it does not require squaring. The equation for MSE is as follows: MSE = 1/n (ei2) , where ei = Fi - Di

QUESTIONS

A food processing company uses a moving average to forecast next months demand. Past actual demand (in units) is as shown in Table
QUESTION 2:

(a) Compute a simple 5-month moving average to forecast demand for month 52. (b) Compute a weighted 3-month moving average, where the weights are highest for the latest months and descend in order of 3, 2 and 1.

QUESTION 3: Lakeside Hospital has used a 9-month, moving-average forecasting method to predict drug and surgical dressing inventory requirements. The actual demand for one item is as shown in Table . Using the previous moving-average data, convert to an exponential smoothing forecast for month 33.

QUESTION 5 A high-valued item has a tracking-signal-action limit of 4 and has been forecast as shown in table. Compute the tracking signal, and indicate whether some corrective action is appropriate.

CONCLUSION
Developing a forecasting system is not easy. However it must be done because forecasting is necessary to any planning effort. In the short run forecasting is needed to predict the requirements for materials , products , services or other resources to respond to changes in demand. Forecast permits adjusting schedules and varying labours and materials. In thre long runm it is required as a base for strategic changes like developing new products , new markets , new serviceas and expanding or creating new facilities. For l;ong vterm forecast that leadt to heavy financial commitment , great care should be taken to derive the forecast. Several approaches should be used. Causal methods such as regression analysis and multiple regressioj analysis are beneficial. These provide a basisi for discussion. Economic factors, product trends, growth factors, and competition as well as myriad other possible variables need to be considered and the forecast need to be adjusted to reflect the influence of each of them. Short and intermediate term forecasting ( such as required for inventory control as well as staffing and material scheduling ) may be satisfied with simpler models such as exponential smoothing with perhaps an adaptive feature or a seasonal index. In these applications, thousands of items are usually forecast at once. The forecasdting routine should therefore be simple and ri=un on a computer. The routine should also detect and respond rapidly to definite short term changes in mind while at the same time ignoring occasional spurious channels. Exponential smoothing , when monitored by management to control the value of alpha , is an effective technique. Web based collaborative forecasting systems that use combinations of the forecasting methods will be the wave of the future in many industries. Information sharing between trading partners with direct links into each firms ERP systems ensure rapid and error free information at a very low and reasonable cost to the user. In summary , forecasting is tough. A perfect forecasting is like a hole one in a golf , great to get but we should be satisfied just to get close to the cup or to push the analogy , just to land on the green. The ideal philosophy is to create the best forecast That you reasonably can and then hedge by maintaining flexibility in the system to account for the inevitable forecast error.

BIBLIOGRAPHY
Websites:
1.www.wikipedia.com 2.www.startupbiz.com 3.www.thepeoplehistory.com

Newspapers:
1.The Times Of India 2.The Hindu 3.The Economic Times

Magazines:
1.India Today 2.Fortune 3.Vogue