Topic 10Demand Forecasting in POM Topic 10 - 0 FORECASTING 1. Forecasting vs. Prediction: Forecasting: Estimating Future by Casting Forward Past Data. Prediction: Estimating Future based on Subjective Considerations other than just Past Data. 2. Three Levels of Forecasting in Operations Management: Long Range Forecasting for Aggregate Demand. Intermediate Range Forecasting for Product Groups. Short Range Forecasting for Individual Item. 3. Forecasting Objectives: Forecasting in POM: Item Demand (Workload for Capacity Planning) Forecasting in Finance: Dollars Revenue (Cash Flow Requirement) Forecasting in Marketing: Unit of Sales (Selling Capability) Topic 10 - 1 2 . If Forecasting is consistently lower than Actual Demand: Topic 10 . If Forecasting is consistently higher than Actual Demand: 2.Forecasting in Operations Forecast for operations Time horizon MGT level Product & Process design Long range Top Capacity Requirement Planning Long/ Intermediate Top / middle Aggregate Production Intermediate Planning Production Scheduling Short Middle Low Impact of Inaccurate Demand Forecasting: (Production Planning based on Demand Forecasting) 1. 3 .Forecasting Systems Topic 10 . .. Econometric Models 3. Regression Analysis 2.. ...Forecasting Techniques Qualitative Approach: 1... Simple Moving Average 2.. ....4 ...... Delphi Methods: (Expert's Subjective Ratings) 2......... Marketing Research and Analysis: (Customer Survey) 3. Quantitative Approach: (Two General Techniques) A: Time Series Analysis: 1.. B: Causal Relationship Models: 1..... Historical Analogy: (Knowledge of Similar Products) 4. Exponential Smoothing 4...... Topic 10 ..... ..... Weighted Moving Average 3........ .. Short Range Forecasting for Scheduling) B.g. (e.. * The Pattern of the Future can be recognized from Past Data.g.) Topic 10 . Short and Intermediate Range Forecasting of Existing Products/Sales/Financial Data/. Quantitative Techniques: (Objective and Quantitative) A. Causal Relationship Models: Used when the Demand of an Item is Dependent (Related to) on other Underlying Factors (not the Past demand).Selection of Forecasting Techniques Principle of Forecasting: * When Past Data are Known as Good Indicator for the Future.5 . Qualitative Techniques: (Subjective and Judgmental) Data Unavailable Unknown Pattern Change Examples: Long Range Forecasting/Sales of New Product/. Time Series Models: Used when Past Demand is A Good Indicator for Future Demand... (e... Topic 10 .6 . Weighted Moving Average: Given (n) and Weights (wi) 3. Simple Moving Average: Given Number of Periods (n) to be Averaged. 2. Simple Exponential Smoothing: Given α (smooth Constant).Three Simple Time Series Models 1. 7 .30. respectively? c) Using simple exponential smoothing and assuming that the forecast for June had been 130. Topic 10 .Exercise #1 Assume that your stock of merchandise is maintained based on the forecast demand.30. 0. compute your forecast sales by each of the three methods requested here. calculate the forecast for September with a smoothing constant alpha of 0. what is the forecast for September with weights of 0. what is the forecast for September? b) Using a weighted moving average. If the distributor’s sales personnel call on the first day of each month. July and August. June Actual demand 140 July 180 August 170 a) Using a simple three-month moving average.20. and 0.50 for June. Ft)|/n (MAD is a Measure of the Size of Forecasting Error.Ft)/n (Bias is a Measure of the Direction of Forecasting Error.Forecasting Error Measurement 1. MAD (Mean Absolute Deviation): MAD = ∑|(At .Ft) 2.) Topic 10 .8 . Forecasting Error in (t): Et = (At .) 3. Bias (Mean Error): Bias = ∑ (Et)/n =∑ (At . Track Signal: TS = Bias/MAD ( -1 ≤TS ≤+1) (TS is a Measure of Forecasting Error in terms of both the "Direction" and the "Size".) 4. 25 and 0. determine the bias.2. 0. 61. 0.1. assuming that the forecast for month 9 is 60. 59. 42. 40. 50.Exercise #2 Month Actual 1 26 2 32 3 39 4 40 5 38 6 47 7 50 8 59 9 56 Demand a) What is the forecast for period 10 using the following models? i) Four period moving average ii) Four period weighted moving average with weights of 0.9 .5 for month 6. 8 and 9 respectively iii) Simple exponential smoothing with alpha =0. 42. 53. 7. MAD and tracking signal. respectively. b) If the forecasts for period 1 to period 9 were 30. How would you improve the forecasting accuracy in this situation? Topic 10 . 35.15. 10. Trend (Linear): General Direction of Demand Growth Seasonal Effects: Pattern that Repeat Every Year (Month/Quarter) Cyclical Effects: Pattern that Repeat other than a Year.Elements of Time Series Analysis Base Level: Demand at Current Time. Random Errors: Unpredictable Random Variations.10 . Topic 10 . Linear Regression Models: (Simple vs.11 .Regression Forecasting Models In many cases.. Multiple) Y = a + b1*X1 + b2*X2 + .. b: Slope) 2.. 1. Regression Models are developed based on Least-Square method. + bn*Xn When n=1.. Y = a + b*X (a: Intercept. the Demand of an Item (dependent variables) is more dependent upon other Leading Factors (independent variables) than the Past Demand. it becomes the Simple Regression Model.. Non-Linear Regression Models: (no general model) Y = a + b1*X1 + b2*X21 Topic 10 . Practical Forecasting Problems 1. Practical Forecasting Issues: Inaccuracy Inconsistency Cost and Accuracy Tradeoff (Simple model may perform better than complicated ones. due to demand pattern changes. New Direction in Forecasting: Integrated (Pyramid) Forecasting System: To Reduce Inconsistency. 2. Combinational Forecasting Models: To Reduce Inaccuracy through: o Model Combinations o Result Combinations Topic 10 .12 .A model that best "fits" the past data may not be the best "Predictive" one for the future.) Data Unavailability Fitness and Predictability . implement. High-accuracy with disadvantages of: need more data/data may be difficult to obtain/models are more costly to design.13 . Long-term best be predicted with regression or similar models. a customer survey may not be practical. Delphi.more accuracy at a cost. historical analogies. and market research Data Availability Is the data available/or be economically obtained? For a new product. Time Span What operations resource be forecasted and for what purpose? Short-term best be forecast with simple time series model. Nature of products and services Is the product/service high cost or high volume? Where is the product/service in its life cycle? Does the product/service have seasonal demand fluctuations? Impulse response and noise dampening An appropriate balance must be achieved between: How responsive the model to change in the actual demand data Topic 10 . Low-Cost approaches.complex econometric models.Criteria for Selecting a Forecasting Method Cost and Accuracy A trade-off between cost and accuracy. executive-committee consensus High-Cost Approaches. and operate/take longer time to use.statistical models. Exercises Demand Forecasting.2 6. Develop a simple linear regression analysis between Finley Heaters’ sales and national housing starts. Manager Joan Newman suspects that the number of units leased during each semester is impacted by the number of students enrolled at the university. Would you recommend that Finley Heaters management use forecast from Part a to plan facility expansion? Why or why not? What could be done to improve the forecast? 2.5 7. Finley Heaters Inc.2 5.Simple Regression 1.14 Number of Units Leased 291 228 252 265 270 240 288 . What percentage of variation in Finley Heaters’ sales is explained by national housing starts? c.7 7. Forecast Finley Heaters’ sales for the next two years.4 7.3 7.3 6. The university enrollment and number of apartment units leased during the past eight semesters is: Semester 1 2 3 4 5 6 7 University Enrollment (thousands) 7.1 Topic 10 . and the company’s production capacity needs to be increased.9 6. Desire to suppress undesirable noise in the demand data.1 6. The company’s management wonders if national housing starts might be a good indicator of the company’s sales.0 Finley Heaters’ Annual Sales (millions of dollars) 57 59 65 78 72 80 86 a. b. Chasewood Apartments is a 300/unit complex near Fairway University that attracts mostly university students. The National Home Builders Association estimates that national housing starts will be 7.0 million for the next two years.9 6.0 6.1 million and 8.4 7. Year 1 2 3 4 5 6 7 National Housing Starts (millions) 6. is a mid sized manufacturer of residential water heaters. Sales have grown during the last several years. The most recent 12 weeks of demand for the CTR 5922 are: Week 1 2 3 Demand (units) 169 227 176 Week 4 5 6 Demand (units) 171 163 157 Week 7 8 9 Demand (units) 213 175 178 Week 10 11 12 Demand (units) 158 188 169 a. IPC’s plant estimates weekly demand for its many materials held in inventory. b. is being studied. what is the exponential smoothing forecast for week 13? c. Topic 10 . Which forecasting method is preferred. b.25 is used and the exponential smoothing forecast for week 11 was 170.76 units.7 246 a.8 6.the AP=3 moving average method or the α=0. How useful do you think university enrollment is for forecasting the number of apartment units leased? Demand Forecasting. What percent of variation in apartment units leased is explained by university enrollment? c. One such part.15 .25 exponential smoothing method? The criterion for choosing between the methods is mean absolute deviation (MAD) over the most recent nine weeks. forecast the number of apartment units that will be leased. Assume that the exponential smoothing forecast for week 3 is the same as the actual demand. If a smoothing constant of 0. Use a simple regression analysis to develop a model to forecast the number of apartment units leased. If the enrollment for next semester is expected to be 6. the CTR 5922. based on university enrollment.Moving Averages 3. Use the moving average method of short-range forecasting with an averaging period of three weeks to develop a forecast of the demand for the CRT 5922 component in week 13.600 students. 39 a. Which alpha value results in the last mean absolute deviation for Months 7-16? Topic 10 . Production manager Josh Kang wants to develop a forecasting system for plastic pellet prices. The past 12 quarters of data are shown below: Year 1 2 3 Quarter 1 2 3 4 1 2 3 4 1 2 3 4 Auditors 132 139 136 140 134 142 140 139 135 137 139 141 a.37 0.41 0. and α=0.39 0. AP=4. Use exponential smoothing to forecast monthly plastic pellet prices. Compute what the forecasts would have been for all the months of historical data for α=0.4.38 0. α=0.44 0.1. Use moving averages to forecast the number of auditors needed next quarter if AP=2.39.Exponential Smoothing 5.38 0. b. Which of these forecasts exhibit the best forecast accuracy over the past six quarters of historical data based on mean absolute deviation? Demand Forecast.36 Month 9 10 11 12 13 14 15 16 Plastic Pellets Price/ Pound 0.35 0.36 0.41 0.43 0. and AP=6.5 if assumed forecast for all α’s in the first month is $0.38 0.16 . The number of Texas tax auditors needed by the Internal Revenue Service varies from quarter to quarter. A toy company buys large quantities of plastic pellets for use in the manufacture of its products. The price per pound of plastic pellets has varied shown: Month 1 2 3 4 5 6 7 8 Plastic Pellets Price/ Pound $ 0. b.39 0.40 0.3.45 0. 4 5.4 16.3 6.Seasonal Forecast 6. Use the best alpha value from part b to compute the forecasted plastic pellets price for month 17. The company believes that the most recent eight quarters of sales should be representative for next year’s sales: Year Quarter 1 1 1 1 1 2 3 4 Sales (millions of dollars) 9.3 14. Demand Forecast.17 .2 5. A computer manufacturer wants to develop next year’s quarterly forecasts of sales revenues for its line of personal computers.c. Topic 10 .0 Use seasonalized time series regression analysis to develop a forecast of next year’s quarterly sales revenue for the line of personal computers.1 Year Quarter 2 2 2 2 1 2 3 4 Sales (millions of dollars) 10.4 4. Recognize the change. They also assume that the trend. Plants should be able to produce multiple products. Moreover. There is no doubt that forecasting is critically important. tools are prone to inaccuracy and. Advanced software tools have at least provided the ability to change formulas globally in the fraction of a second. and other key elements should be developed with an eye for flexibility. Better processes are required. Something obviously has to be done. relying solely on these numerical forecasting methods to drive business would be an exercise in corporate hara-kiri. There are more than 100 different quantitative forecasting methods available. Following are some ways to begin. a tsunami. if necessary. But.Techniques to Support Better Forecasting Company leaders at a manufacturer of industrial fuel pumps decided to discontinue some of their ~ products. forecasting has evolved from a set of principles to a set of tools. diesel electricity generators caused the pumps to be back in high demand. how is an accurate forecast achieved? Normally associated with numbers and formulas. They dismissed vendors and cancelled all existing agreements related to the phasedout pumps. season. forecasting is a kind of magic box that uses certain inputs to determine the products that the market expects. Time-series methods extrapolate existing trends and include seasonal and cyclical indices. The ideal situation would be to have processes that are responsive to customer needs and do not require a forecast to function. Every operations management professional has a forecasting nightmare of his or her own resembling this one. Institute flexibility. But these models have an inherent limitation in the number of factors they use because it is impossible to include all the key data. not the way it is done. something that seems insignificant today all of a sudden may become a key driver. A food shortage. and countless other events have the potential to completely alter the basic rules of business. Operations management professionals have to appreciate the variability in a situation. hence. Employees and managers must have the necessary skill and-more importantly-the right attitude to be able Topic 10 . terrorism. and the price and availability of raw material often varies at a speed defying logic. given the nature of abrupt changes. Even the smallest incidents can have a dramatic impact. The manufacturer thus had to start from scratch in order to revive a product that otherwise could have been a cash cow. product design. a boom in small. Not long after. or cycle will have a predictable and similar effect every time.18 . a change in walking shoes does not improve anything. and they must be resistant to inaccurate forecasts. One idea is to create better forecasting models that are monitored and improved in real time. creating an accurate model seems even more difficult. The foundations: Over the years. however. The point is: When the path is wrong. Market conditions change at an incredible pace. They must bear in mind that sporadic events can occur and change their businesses-and these people must understand that such events cannot be forecast. Manufacturing facilities. create a negative impression. Investing efforts and resources into seemingly better tools also would lead to destruction-albeit more slowly. Vendors must be able to respond to a change of scale and scope without a major impact on their pricing. Complex econometric and regression-based methods try to isolate the individual components causing demand in order to create a forecasting model. While principles are generic and do not change. rising fuel prices. vendors. which all begin with the simple assumption that the past will repeat in the future. Given these dynamic conditions. Operations management professionals must alter the way forecasting is used. Operating with high speed and accuracy ensures the forecasting model will work on current information. Data on actual customer usage should be tracked whenever possible. For example. a few components now are stored and forecast only at the central location. As such. Accurate and fast information is the lifeline of a strong business. if 70 percent of output can be predicted with 95 percent accuracy. but it is nonetheless necessary for a firm's survival-especially when an organization has multiplying product variants in a dynamic global marketplace. This is more important-and more possible than ever before. if the cumulative lead time is 30 days. and distribution. operations management professionals must refocus their efforts to create processes that can deliver standard output with forecasts of limited accuracy. the market has to be approximated by at least 30 days. manufacturing. Customers expect multiple. significantly increasing accuracy. Monitor international politics. Given that the stakes of the game have changed. Instead of forecasting all the components at each location. Postpone. Buying and selling internationally involves a lot of risk. Software solutions offer some assistance. that means 25 percent of the errors in the remaining 30 percent of the output would have a less significant impact. Forecasting should be moved upstream.to change their responsibilities according to current requirements. social issues. and a company must be able to change the volume of these products as necessary. Then. The benefits of instituting flexibility almost always outweigh the costs. Segment products. Unless a firm is in a very dynamic market. Make "small" work. and technology tools should be used to enable information entry once. Company leaders decided to shift all the slow-moving spare parts to a central warehouse. Forecasting is bound to be inaccurate. unique products. they would be flown to the different regions on an as-needed basis. For example. Rather than waiting for a batch of goods. Standardization is not the antonym of flexibility. Increase the speed of information transfer. If small batches can reduce this time to 10 days. Forecasting never can predict such events. the market has to be pre-empted by only 10 days. they're in business to make more money. then the firm could have absorbed market fluctuations much more easily. the rules need to be altered. but the current tools never will be 100 percent effective. Recognize the goal. Smaller vehicles can be used to transport material more frequently. Forecasting is merely a tool that helps along the way. So. Technology enables us to do final assembly much closer to the customer and without any major increase in cost. Politics. Thus. The shorter the term. Elevate forecasting. Topic 10 . and. the processes should be changed to make them work. and operations management professionals must recognize this and buffer the forecasts when necessary. Not all products change regularly. it becomes much more likely that employees can react accurately. Rework business rules. there always will be products that are more stable than others. every aspect of business must be rewired to enable small batch sizes. Results of forecasting processes must be monitored at the highest level in order to develop other processes and reduce dependence on forecasts. an after-sales service firm stored fast-moving components at all its regional depots.19 . Plus. at the point of occurrence. Delivering or picking up goods from multiple sites and then returning to the original location with them should be considered. work must be able to proceed on individual pieces. If company leaders at the fuel pump manufacturer from the beginning of this article had kept basic product design constant and limited variation to modules. Senior managers must recognize the limitations of the process and lead the necessary changes in design. and economics have to be monitored to create scenarios of possible impact. Firms are not in business to make accurate forecasts. the better the forecast. as well. wherever small batch sizes are not economical. as well. Putting these items aside and setting a standard schedule for them reduces complexity. Forecasting cannot be merely an operational tool. Keep in mind: Making small work means that goods will reach the market much faster. It essentially means that the changes to a base product must be incremental. Standardize products. based on mathematical modeling. which are based on opinions. Information technology has enabled forecasts to drive entire supply chains and enterprise resources plan ning systems. and it is supported by numerous research studies. and the automated forecasts simply were not accurate enough. can be developed to capture this human judgment. Nike leaders acknowledged that they would be taking a major inventory write-off due to inaccurate forecasts from the automated system. this is something that managers find to be effective. Nike's experience with automated statistical forecasts is not an isolated case. rapidly shifting markets. However. issue of CIO magazine. improved quality. Sanders. The problem. anticipating future demands. According to the July 15. Relying on statistical forecasts alone can be ineffective in this highly complex environment. Practitioners often have up-to-date knowledge of changes and events occurring in their environment that can influence the forecast. as it turned out. effectively scheduling production. While causal models.(See Figure 1. PhD. Nike had entirely too much inventory of slow-moving items and a major shortage of popular sellers. Increasingly. such as regression. This informa tion often is last-minute and cannot easily be incorporated into the statistical forecast. global competition has created an environment characterized by uncertainty. Benefits and drawbacks Judgmental and statistical forecasting methods each bring valuable information to the forecasting process.) The best forecasting approach is one that leverages the strengths of both methods. Simultaneously.Question: Summarize what you have learned from reading this article. and reducing inventories. and compressed cycle times. Topic 10 . The result has been a sharp rise in forecasting's complexity and historical data that are often of limited value for predicting the future. Over the past few years. was that Nike executives relied exclusively on automated forecasts without any judgmental checks. however. or statistical forecasting methods. Each category has unique strengths and weaknesses. and greater product choice. the role of forecasting has become especially significant due to more competitive market pressures. nine months after implementing a much publicized i2 system. managers can choose from either judgmental forecasting methods.20 . combining judgmental and statistical forecasting requires following well-established rules. OUTLOOK-Warm and Sunny By Nada R. Getting the best forecast by combining judgmental and statistical methods Accurate forecasting always has been a critical organizational capability for effective business planning. Good forecasts are essential for identifying and new market opportunities. Customers are demanding increasingly shorter response times. 2003. When making forecasts. Consider the case of Nike's $400 million failure in 2000 with demand forecasting software. such refinements are impractical for making inventory replenishment decisions when there are thousands of different items to be controlled. Unfortunately. such as a new competitor entering the marketplace or a snow storm delaying a shipment.Judgmental forecasts also have the advantage of being able to incorporate "soft" or "inside" information that can be helpful predictor is in changing environments. Statistical forecasts also are based on historical data and are ineffective when market conditions change. statistical forecasts can process large amounts of data at one time. consider the manager who is optimistic one day after a large sale or highly pessimistic another day following a sales slump. lack of consistency. when managerial involvement would be timeconsuming and costly. Also. statistical forecasts are based on . often are inaccurate due to limitations in human cognitive ability. the generated forecasts can't be accurate. Unlike judgmental-also called managerial-forecasts. however. Such events often lead people to inadvertently bias their forecasts. mathematical principles and are typically generated by any one of the many software packages available. People naturally have a limited attention span and can process only a restricted amount of information at a time. Biases include optimism. statistical models are only as good as the data upon which they are based. These types of information might include a rumor about a competitor launching a new product or an impending labor strike. In addition. For example. which can result in degradation of accuracy. judgmental forecasts can be biased because they are subjective.21 . wishful thinking. When changes occur in the data that are not incorporated in the model. and political manipulation. Judgmental forecasts. However. This is particularly effective for generating forecasts for a large number of stock keeping units (SKUs). research has documented that judgmental forecasts are influenced by short-term memory and the inability of forecasters to understand causal relationships. always producing the same forecast for the same data set. Similarly. Statistical forecasts are consistent. and unbiased. objective. Topic 10 . Structuring available data through a procedure or decision- Topic 10 . Domain knowledge is information managers gain through on-the-job expe rience. The adjustment should compensate for specific events not captured by the statistical model or not yet observed in the time series. Becoming familiar with their environment.A winning combination More and more. Domain knowledge enables managers to evaluate the importance of specific contextual informa tion. Rule following In order to gain the best from both forecasting methods. it is critical to understand rules on how and when statistical forecasts should be adjusted. If this information is not contained in the statistical forecasting model. Managers with domain knowledge understand which cues in the environ ment are significant and which are unimportant. This method requires managers to adjust the statistical fore cast up or down based on their opinions. Structure the judgmental adjustment process. Judgmental adjustment of the statistical forecast can improve accuracy if the forecaster can identify these patterns in the data and incorporate this information in the adjustment." Managerially adjusting statistical forecasts often can improve forecast accuracy by including information not available to the statistical model. is managerial adjustment of statistical forecasts. Judgmental and statistical forecasts can ' be combined in different ways in order to take advantage of their individual strengths. and labor strikes. however. successful forecasting uses composite methodologies. often called a "managerial override. One of the disadvantages of human judgment is the limited ability to consider and process large amounts of information. if performed incorrectly. Adjust statistical forecasts when there are known changes in the environment . the manager can incorporate the information by adjusting the statistical forecasts. However. or new policies that may affect the forecast. an impending strike. Specific information available in the forecast environment is called contextual information. These events can include machines down due to repair. managers learn many cause-and-effect relationships and environmental cues. advertising campaigns. By far the most popular method in practice.22 . Research studies repeatedly have found that judgmental adjustment is more likely to improve accuracy when the adjustment is based on domain knowledge. Managers should follow established rules for effectively adjusting statistical forecasts. statistical forecasts should account for discon tinuities or pattern changes in the data. One way is to take a mathematical average of both methods to generate a final forecast. Examples of contextual information include a price increase. Only practitioners with domain knowledge should adjust statistical forecasts. For example. judgment should incorporate information that is not captured by the statistical forecast. To be useful. adjustments can cause inaccuracy due to inherent human biases. thereby. However. managers may be responsible for hundreds of different SKUs. managers can evaluate what types of adjustments led to the greatest improvement and which adjustments were ineffective . the managers in question had been responsible for generating forecasts over a period of years. Many forecasting situations do not provide this advantage. forecasting process structure. such as that generated by a computer-aided decision support system. Only when forecasters know of events and information that influence the forecast should judgment be used to adjust it. why the combining forecasting approach may give you the best results? Topic 10 . Document all judgmental adjustments made and measure forecast accuracy Like all forecasts. The benefits of a more refined forecast need to make financial sense. and adequate feedback. managers must decide what type of forecasting procedure to use and whether to adjust a statistical forecast. are these benefits significant in terms of cost? The cost of managerial involvement can be high when making forecast adjustments and developing domain knowledge. In addition. This may be the case for forecasting demand for a brand-new product or for long range strategic forecasting decisions where information is hard to quantify. Structuring can be complex. For example. Also. Questions: Based on this article. quantifiable.enabling future improvement. accurate records must be kept over time. When good. judgmentally adjusted forecasts need to be measured using forecast accuracy measures. to succeed. Judgmental adjustment has been shown to lead to greater improvements in accuracy if the process is structured. Managers should be selective as to which forecasts they adjust. as opposed to an ad hoc adjustment. The important thing is that it is used. First. They kept records of their forecasts and received regular feedback. reliance should be placed on statistical forecasts. achieving high levels of knowledge and familiarity may be impossible. an important aspect of accuracy is ensuring that the numbers and the arithmetic are correct. In such environments. This depends on the amount and type of available information. in inventory management. A sufficient amount of quantifiable data need to exist in order to apply a statis tical forecast. Repetition and good feedback over a long period of time enabled these managers to develop expertise.support system is helpful in forecasting and decision making. records should be kept of all adjustments made and the reasons for the adjustment. forecasts may need to be based solely on judgment. in studies where managers’ judgmental forecasts significantly outperformed statistical forecasts. Current conditions The rules provided raise a number of implications for managers. Over time. and markets.23 . Though there are benefits with judgmental adjustment. Judgmental adjustments only should be made when there is contextual information in the presence of domain knowledge. historical data are available. For example. This process can have a powerful effect on improving forecast accuracy. focusing on a smaller number of forecasts will enable a manager to achieve greater accuracy. Another issue to consider is the cost of managerial involvement. There often are changes in product mix. In addition. Without such data. giving them the tools to create more effective forecasts. or as simple as using a paper and pencil. customer mix. 11) What is the primary difference between a causal model and a time series model for forecasting? 12) Differentiate between the projection type of forecasting and the predictive type of forecasting. (4) Why are there different considerations in selecting a forecasting model regarding three different forecasting horizons: short-term. MAD.Review Questions for Topic 10: < DEMAND FORECASTING> Be prepared to discuss the following cases: (1) Differentiate between qualitative and quantitative forecasting techniques.24 .under what conditions these two techniques will be preferred to use in practice. “tracking signal” and "random errors" in forecasting. Discuss . a weighted moving average. (2) Be prepared to compute a forecast using a simple moving average. Topic 10 . (5) How is the mean absolute deviation (MAD) of a forecast series computed? Why is it computed? (7) What is the impact of using a large (or a small value of) in computing an exponentially weighted forecast? (8) What is the impact of using a large number of period (or a small number of) (n) in computing a simple (or weighted) moving average forecast? (9) Generally. (3) What is the “principle of forecasting”? Brief explain. medium-term. and exponential smoothing. and long-term. how are seasonal effects included in exponential smoothing? 10) Explain the differences between "bias".