Presentation is loading. Please wait.

Presentation is loading. Please wait.

Forecasting Chapter 9. Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 2 1. Define Forecast.

Similar presentations


Presentation on theme: "Forecasting Chapter 9. Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 2 1. Define Forecast."— Presentation transcript:

1 Forecasting Chapter 9

2 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 2 1. Define Forecast.

3 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 3 Forecasting  Forecast – An estimate of the future level of some variable.  Why Forecast?  Assess long-term capacity needs  Develop budgets, hiring plans, etc.  Plan production or order materials

4 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 4 2. Define Planning.

5 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 5 10 -5  Planning - Determining what is needed, and making arrangements to get it, in order to achieve objectives. PLANNING

6 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 6 3. What are the financial benefits of effective planning?

7 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 7 10 -7  Increasing Alternatives  Management has more options if it plans ahead.  Profitability Enhancement  Planning can both reduce costs and increase sales.  Uncertain future The further ahead we plan, however, the less we know about future conditions. There is a tradeoff between increasing alternatives and increasing uncertainty. Financial Benefits of Effective Planning

8 10 -8 Planning Horizon – The distance into the future one plans. Looking into the Future: The Planning Horizon

9 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 9 4. What is a contingency plan?

10 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 10 10 - 10  Contingency Plans – Alternative or back-up plans to be used if an unexpected event makes the normal plans infeasible. Contingency Plan

11 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 11 5. What are three common types of forecasts?

12 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 12 Types of Forecasts  Demand  Firm-level  Market-level  Supply  Number of current producers and suppliers  Projected aggregate supply levels  Technological and political trends  Price  Cost of supplies and services  Market price for firm’s product or service

13 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 13 6. What are the four laws of forecasting?

14 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 14 Laws of Forecasting  Forecasts are almost always wrong by some amount (but they are still useful).  Forecasts for the near term tend to be more accurate.  Forecasts for groups of products or services tend to be more accurate.  Forecasts are no substitute for calculated values.

15 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 15 7. What are the two types of forecasting models?

16 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 16 Forecasting Models  Qualitative forecasting techniques – Forecasting techniques based on intuition or informed opinion.  Used when data are scarce, not available, or irrelevant. Do not use past data. Usually used when such data is not available (such as planning for a new product).  Customer surveys, expert opinions, etc

17 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 17 Qualitative Forecasting Models  Market surveys  Build-up forecasts  Life-cycle analogy method  Panel consensus forecasting  Delphi method

18 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 18 Forecasting Models  Quantitative forecasting models – Forecasting models that use measurable, historical data to generate forecasts.  Time series and causal models

19 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 19 Quantitative Forecasting Methods  Time series forecasting models – Models that use a series of observations in chronological order to develop forecasts.  Causal forecasting models – Models in which forecasts are modeled as a function of something other than time.

20 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 20 Selecting a Forecasting Method Figure 9.2

21 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 21 7. What are components of a time series?

22 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 22 10 - 22  There are four potential components of a time series:  Cycles A pattern that repeats over a long period of time (such as 20 years). Cycles are less important for demand forecasting, since we rarely have 20 years’ worth of data.  Trend  Seasonality  Randomness Components of a Time Series

23 10 - 23 Components of a Time Series Trend – Component of a time series that causes demand to increase or decrease. Exhibit 10.6 Example of a Time Series with Trend

24 10 - 24 Seasonality – A pattern in a time series that repeats itself at least once a year. Exhibit 10.7 Time Series with Seasonality Components of a Time Series

25 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 25 Time series with Trend and Seasonality Figure 9.4

26 10 - 26 Random Fluctuation – Unpredictable variation in demand that is not due to trend, seasonality, or cycle. Exhibit 10.8 Time Series with Random Fluctuation Components of a Time Series

27 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 27 Time series with randomness Figure 9.3

28 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 28 9. What are the various time series techniques?

29 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 29 Last Period Model  Last Period Model - The simplest time series model that uses demand for the current period as a forecast for the next period. F t+1 = D t where F t+1 = forecast for the next period, t+1 and D t = demand for the current period, t

30 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 30 Last Period Model Table 9.3Figure 9.5

31 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 31 Moving Average Model  Moving Average Model – A time series forecasting model that derives a forecast by taking an average of recent demand value.

32 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 32 Moving Average Model 3-period moving average forecast for Period 8: =(14 + 8 + 10) / 3 =10.67 PeriodDemand 112 215 311 49 510 68 714 812

33 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 33 Weighted Moving Average Model  Weighted Moving Average Model – A form of the moving average model that allows the actual weights applied to past observations to differ.

34 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 34 Weighted Moving Average Model 3-period weighted moving average forecast for Period 8= [(0.5  14) + (0.3  8) + (0.2  10)] / 1 = 11.4 PeriodDemand 112 215 311 49 510 68 714 812

35 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 35 10. What is the formula for simple exponential smoothing using a sophisticated weighted moving average?

36 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 36 Exponential Smoothing Model  Exponential Smoothing Model – A form of the moving average model in which the forecast for the next period is calculated as the weighted average of the current period’s actual value and forecast.

37 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 37 Exponential Smoothing Model a =.3 PeriodDemandForecast 15040 246.3 * 50 + (1-.3) * 40 = 43 352.3 * 46 + (1-.3) * 43 = 43.9 448.3 * 52 + (1-.3) * 43.9 = 46.33 547.3 * 48 + (1-.3) * 46.33 = 46.83 6.3 * 47 + (1-.3) * 46.83 = 46.88

38 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 38 Causal Forecasting Models  Linear Regression  Multiple Regression  Examples:

39 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 39 Causal - Linear Regression 

40 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 40 Forecast Accuracy How do we know:  If a forecast model is “best”?  If a forecast model is still working?  What types of errors a particular forecasting model is prone to make? Need measures of forecast accuracy

41 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 41 11. What are the two kinds of forecasting errors?

42 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 42 10 - 42 Forecast Accuracy  Forecast error is the actual demand minus the forecast demand.  Absolute Error: how far “off” are we, in absolute terms?  Measured by mean absolute deviation (MAD) or mean squared error (MSE)  Forecast Bias: Are we consistently high or low?  A forecast should be unbiased (low forecasts are as frequent as high forecasts)  Bias is measured by mean forecast error (MFE) or running sum of forecast error (RSFE)

43 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 43 10 - 43  The ideal value for both is zero, which would mean there is no forecasting error  The larger the MAD or MSE, the less the accurate the model Forecast Accuracy Two similar approaches are used to measure absolute forecast error MAD is the mean of the absolute values of the forecast errors MSE is the mean of the squared values of the forecast errors

44 Calculating MAD

45 Calculating MSE

46 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 46 10 - 46 Forecast Bias  Forecast Bias: Tendency of a forecast to be too high or too low.  Mean forecast error (MFE)  The mean of the forecast errors  Running sum of forecast errors (RSFE)  The sum of forecast error, updated as each new error is calculated.  Ideal measure is zero which indicates no bias.  Positive means forecast tends to low  Negative means forecast tends to high

47 Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 47 Forecast Bias: Calculating MFE and RSFE Mean Forecast Error = 1.00 RSFE (period 8) = 8


Download ppt "Forecasting Chapter 9. Copyright © 2013 Pearson Education, Inc. publishing as Prentice Hall9 - 2 1. Define Forecast."

Similar presentations


Ads by Google