topic 6 - forecasting

Upload: kalpak-iyer

Post on 10-Apr-2018

219 views

Category:

Documents


0 download

TRANSCRIPT

  • 8/8/2019 Topic 6 - Forecasting

    1/77

    OperationsManagement

    Forecasting

    Prof. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    2/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Prediction Prediction

    Reflects judgment after taking all

    considerations into account

    Involves anticipated changes in

    future that may or may not happen

    Based on intuition

    It can be biasedNo error analysis

    Based on unique representations

  • 8/8/2019 Topic 6 - Forecasting

    3/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Forecasting

    Forecasting

    Involves the projection of the pastinto the future

    Estimating the demand on the basis

    of factors that generated thedemand

    Based on theoretical model

    It is objective

    Error Analysis is possible

    Results are replicable

  • 8/8/2019 Topic 6 - Forecasting

    4/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    A forecast is an estimate of

    a future event achieved by

    systematically combiningand casting forward , in a

    predetermined way, data

    about the past.

    DEFININGFORECASTING

  • 8/8/2019 Topic 6 - Forecasting

    5/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Forecasting vs. Prediction

    Forecasting Prediction

    Involves the projection of the past intothe future

    Reflects managements judgment aftertaking all considerations into account

    Estimating the demand on the basis of

    factors that generated the demand

    Involves anticipated changes in future

    that may or may not generate thedemand

    Based on theoretical model Based on intuition

    It is objective It can be biased

    Error Analysis is possible No error analysis

    Results are replicable Based on unique representations

  • 8/8/2019 Topic 6 - Forecasting

    6/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Forecasting is the start

    of any planning activity.

    The main purpose of

    forecasting is to estimatethe occurrence, timing or

    magnitude of future

    events.

    WHYFORECASTING?

  • 8/8/2019 Topic 6 - Forecasting

    7/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    The Decision making Cycle

    Forecasts help management take into account external

    factors that impact operations and reduce the uncertainty.

    The decision making cycle reflects how organizations use

    forecasting to reduce the impact of market forces on abusiness.

  • 8/8/2019 Topic 6 - Forecasting

    8/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Decision Types requiring Forecasting

    Forecasting horizon in years

    Specific demand

    Aggregate

    demand

    Strategies &

    facilities

    Types of Decision

    Short term

    Long term

    Planning

    Medium

    term

  • 8/8/2019 Topic 6 - Forecasting

    9/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru9

    Demand Forecasting

    Demand Forecasting is theactivity of estimating the quantityof a product or service that

    consumers will purchase.

    Demand forecasting involvestechniques including both formal

    and informal methods.

    Demand forecasting may be used

    in making scheduling decisions, in

    assessing future capacity

    requirements, or in making

    decisions on whether to enter

    a new market.

  • 8/8/2019 Topic 6 - Forecasting

    10/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru 10

    A

    B(4) C(2)

    D(2) E(1) D(3) F(2)

    Dependent Demand:

    Raw Materials,

    Component parts,

    Sub-assemblies, etc.

    Independent Demand:

    Finished Goods

    Types of Demand

    Aggregate Planning is concerned with aggregate demandi.e. the amount of a particular economic goodor service that a consumer or group of consumers

    will want to purchase (at a given price).

  • 8/8/2019 Topic 6 - Forecasting

    11/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    The firm should be able toforecast ideal levels of

    inventory.The relative cost of holdingeither too much or too littleinventory might be differentfrom the ideal levels because

    of poor forecasts of demand. If demand were less than

    expected, the firm would incurextra inventories and the cost ofholding them.

    If demand were greater than

    expected, the firm would incurback-order or shortage cost andthe possible opportunity costs oflost sales or a lower volume ofactivity.

    Demand and Costs

  • 8/8/2019 Topic 6 - Forecasting

    12/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Demand Management

    Do I manage demand ?

    Do I live with it?

    Demand management describes the process ofinfluencing the volume of consumption of the

    product or service through management decision

    so that firms can use their resources and

    production capacity more effectively.

  • 8/8/2019 Topic 6 - Forecasting

    13/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru13

    Can take an active role toinfluence demand. For example,air conditioner manufacturesoffer discounts for theirproducts in winter , when

    demand for the products falls. Demand management is also

    used to spread demand moreevenly. Telephone companies,world over, offer discounts for

    calls made during late hours orat night.

    Can take a passive role andsimply respond to demand

    Independent Demand

    What to do?

  • 8/8/2019 Topic 6 - Forecasting

    14/77Operations Management

    Eight Steps toEight Steps to

    ForecastingForecasting

    Determining the use of theDetermining the use of theforecast--what are theforecast--what are the

    objectives?objectives?

    Select the items to be forecastSelect the items to be forecast

    Determine the time horizon ofDetermine the time horizon ofthe forecastthe forecast

    Select the forecasting model(s)Select the forecasting model(s)

    Collect the dataCollect the data

    Validate the forecasting modelValidate the forecasting model Make the forecastMake the forecast

    Implement the resultsImplement the results

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    15/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    15

    Quantitative

    Time Series Analysis Exponential Method

    Regression Analysis

    Simulation/ Scenario PlanningQualitative (Judgmental)

    Types of Forecasts

  • 8/8/2019 Topic 6 - Forecasting

    16/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Time Series1. Extrapolation

    2. Moving average Method

    Exponential Method

    1. Simple Exponential Method2. Double Exponential Method

    3. Triple Exponential Method

    Regression Analysis

    1. Simple Regression Analysis2. Multiple Regression Analysis

    QuantitativeApproach

  • 8/8/2019 Topic 6 - Forecasting

    17/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Time Series

    There are five basic patterns in which demand varieswith time that have been identified:

    Horizontal Trend

    Seasonal Cyclical Random

  • 8/8/2019 Topic 6 - Forecasting

    18/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Graphical Representation

    Time

    Demand(units)

    Constant

  • 8/8/2019 Topic 6 - Forecasting

    19/77Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Moving Average Method

    Where:

    Ft+1

    is the moving average for the period t+1,

    At, A

    t-1, A

    t-2, A

    t-3etc. are actual values for the corresponding

    period, and n is the total number of periods in theaverage

    Or it can be written as:

    F =A + A + A +...+A

    nt

    t-1 t-2 t-3 t-n

    The general formula for moving average is:

    Ft+1 = (At + At-1 + At-2 + At-3 +

    + At-n+1 ) / n

  • 8/8/2019 Topic 6 - Forecasting

    20/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Simple Moving Average Problem

    Week Demand

    1 650

    2 678

    3 7204 785

    5 859

    6 920

    7 850

    8 7589 892

    10 920

    11 789

    12 844

    F = A + A + A +...+An

    t t-1 t-2 t-3 t-n

    Question: What are the 3-week and 6-week movingaverage forecasts fordemand?

    Assuming you only have 3weeks and 6 weeks of actualdemand data for therespective forecasts

    Question: What are the 3-week and 6-week moving

    average forecasts fordemand?

    Assuming you only have 3weeks and 6 weeks of actual

    demand data for therespective forecasts

  • 8/8/2019 Topic 6 - Forecasting

    21/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Week Demand 3-Week 6-Week

    1 650

    2 678

    3 720

    4 785 682.67

    5 859 727.676 920 788.00

    7 850 854.67 768.67

    8 758 876.33 802.00

    9 892 842.67 815.3310 920 833.33 844.00

    11 789 856.67 866.50

    12 844 867.00 854.83

    F4=(650+678+720)/3

    =682.67F7=(650+678+720

    +785+859+920)/6

    =768.67

    Calculating the moving averages gives us:

    The McGraw-Hill Companies, Inc.,

  • 8/8/2019 Topic 6 - Forecasting

    22/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Problem (2) Data

    Week Demand1 820

    2 775

    3 680

    4 655

    5 620

    6 600

    7 575

    Question: What is the 3week moving average

    forecast for this data?Assume you only have 3weeks and 5 weeks ofactual demand data for the

    respective forecasts

    Question: What is the 3week moving average

    forecast for this data?Assume you only have 3weeks and 5 weeks ofactual demand data for therespective forecasts

  • 8/8/2019 Topic 6 - Forecasting

    23/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Problem (2) Solution

    Week Demand 3-Week 5-Week

    1 820

    2 7753 680

    4 655 758.33

    5 620 703.33

    6 600 651.67 710.00

    7 575 625.00 666.00

    F4=(820+775+680)/3

    =758.33F6=(820+775+680

    +655+620)/5

    =710.00

  • 8/8/2019 Topic 6 - Forecasting

    24/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Weighted Moving Average

    While the moving average formula implies an equal weightbeing placed on each value that is being averaged, the

    weighted moving average permits an unequal weighting on

    prior time periods

    While the moving average formula implies an equal weight

    being placed on each value that is being averaged, the

    weighted moving average permits an unequal weighting on

    prior time periods

    The general formula for the weighted moving average then

    changes to:

    Ft+1 = wtAt + wt-1 At-1 + wt-2 At-2 + wt-3 At-3 +

    + wt-n+1 At-n+1Where:

    Ft+1 is the weighted moving average for the period t+1,wt is the weighing factor, and wt = 1

  • 8/8/2019 Topic 6 - Forecasting

    25/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru25

    Weights:

    t-1 .5

    t-2 .3

    t-3 .2

    Week Demand

    1 650

    2 678

    3 720

    4

    Question: Given the weekly demand and weights,what is the forecast for the 4th period or Week 4?

    Question: Given the weekly demand and weights,

    what is the forecast for the 4th period or Week 4?

    Note that the weights place more emphasis onthe most recent data, that is time period t-1

    Note that the weights place more emphasis onthe most recent data, that is time period t-1

    F = w A + w A + w A +...+w At 1 t-1 2 t-2 3 t-3 n t-n

    w = 1ii=1

    n

    wt = weight given to time period toccurrence (weights must add to one)

    wt = weight given to time period toccurrence (weights must add to one)

    The formula for the moving average can also be written as:The formula for the moving average can also be written as:

  • 8/8/2019 Topic 6 - Forecasting

    26/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru26

    Problem Solution

    Week Demand Forecast

    1 650

    2 678

    3 720

    4 693.4

    F4 = 0.5(720)+0.3(678)+0.2(650)=693.4

  • 8/8/2019 Topic 6 - Forecasting

    27/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru27

    Problem (2) Data

    Weights:

    t-1 .7

    t-2 .2t-3 .1

    Week Demand

    1 820

    2 775

    3 680

    4 655

    Question: Given the weekly demand informationand weights, what is the weighted movingaverage forecast of the 5th period or week?

    Question: Given the weekly demand informationand weights, what is the weighted movingaverage forecast of the 5th period or week?

  • 8/8/2019 Topic 6 - Forecasting

    28/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru28

    Problem (2) Solution

    Week Demand Forecast

    1 820

    2 7753 680

    4 655

    5 672

    F5 = (0.1)(755)+(0.2)(680)+(0.7)(655)= 672

  • 8/8/2019 Topic 6 - Forecasting

    29/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Exponential method is atechnique that is applied to time

    series data, either to producesmoothed data for presentation,

    or to make forecasts.

    Premise: The most recent

    observations might have thehighest predictive value.Therefore, we should give moreweight to the more recent timeperiods when forecasting

    ExponentialMethod

  • 8/8/2019 Topic 6 - Forecasting

    30/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru30

    Exponential Smoothing Model

    The exponential relationship be written as:

    Ft+1 = Dt + (1 - ) FtWhere:

    Dtis the actual value

    Ftis the forecasted value

    is the weighting factor, which ranges from 0 to 1

    t is the current time period.

    The variance is given by:

    (Dt - Ft+1 )2/n = Variance

  • 8/8/2019 Topic 6 - Forecasting

    31/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru31

    Problem (1) Data

    Week Demand

    1 820

    2 775

    3 6804 655

    5 750

    6 802

    7 7988 689

    9 775

    10

    Question: Given the weeklydemand data, what are theexponential smoothing forecastsfor periods 2-10 using =0.10and =0.60?Assume F1=D1

    Which is a better choice?

    Question: Given the weeklydemand data, what are theexponential smoothing forecastsfor periods 2-10 using =0.10

    and =0.60?Assume F1=D1

    Which is a better choice?

  • 8/8/2019 Topic 6 - Forecasting

    32/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru32

    Week Demand 0.1 0.6

    1 820 820.00 820.00

    2 775 820.00 820.00

    3 680 815.50 793.00

    4 655 801.95 725.205 750 787.26 683.08

    6 802 783.53 723.23

    7 798 785.38 770.49

    8 689 786.64 787.00

    9 775 776.88 728.20

    10 776.69 756.28

    Answer: The respective alphas columns denote the forecastvalues. Note that you can only forecast one time period into thefuture.

    Answer: The respective alphas columns denote the forecastvalues. Note that you can only forecast one time period into thefuture.

    F3=775x0.1 + (1-0.1)x820 =815.50

  • 8/8/2019 Topic 6 - Forecasting

    33/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru33

    Answer: Variance0.3 = 6675.61 and Variance0.6 = 5369.39. Thereforealpha as 0.6 is a better choice

    Answer: Variance0.3 = 6675.61 and Variance0.6 = 5369.39. Thereforealpha as 0.6 is a better choice

    Demand 0.1 D-W (D-W)2 0.6 D-W (D-W)2

    820 820.00 0.00 0.00 820.00 0.00 0775 820.00 -45.00 2025.00 820.00 -45.00 2025

    680 815.50 -135.50 18360.25 793.00 -113.00 12769

    655 801.95 -146.95 21594.30 725.20 -70.20 4928.04

    750 787.26 -37.26 1387.94 683.08 66.92 4478.286

    802 783.53 18.47 341.16 723.23 78.77 6204.398

    798 785.38 12.62 159.35 770.49 27.51 756.6461

    689 786.64 -97.64 9533.35 787.00 -98.00 9603.436

    775 776.88 -1.88 3.52 728.20 46.80 2190.348

    53404.87 42955.15

    Which one?

  • 8/8/2019 Topic 6 - Forecasting

    34/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru34

    Plotting the Solution

    5 0 0

    6 0 0

    7 0 0

    8 0 0

    9 0 0

    1 2 3 4 5 6 7 8 9 1 0

    W e e

    Demand

    D e m a

    0 . 1

    0 . 6

    Note how that the smaller alpha results in a smootherline in this exampleNote how that the smaller alpha results in a smootherline in this example

  • 8/8/2019 Topic 6 - Forecasting

    35/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru35

    Problem (2) Data

    Question: What are theexponential smoothingforecasts for periods 2-5using a =0.5?

    Assume F1=D1

    Question: What are theexponential smoothing

    forecasts for periods 2-5using a =0.5?

    Assume F1=D1

    Week Demand

    1 8202 775

    3 680

    4 6555

  • 8/8/2019 Topic 6 - Forecasting

    36/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Problem (2) Solution

    Week Demand 0.5

    1 820 820.00

    2 775 820.00

    3 680 797.50

    4 655 738.75

    5 696.88

    F1=820x0.5 + (1.0-0.5)x820 =

    820F3=775x0.5 + (1.0-0.5)x820

    =797.75

  • 8/8/2019 Topic 6 - Forecasting

    37/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Exponential Smoothing & SimpleMoving Average

    An exponentially weighted moving average with

    a smoothing constant a, corresponds roughly toa simple moving average of length (i.e., period)

    n, where and n are related by:

    = 2/(n+1) OR n = (2 - )/ .

  • 8/8/2019 Topic 6 - Forecasting

    38/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Double and Triple Smoothing

    An exponential smoothing over an alreadysmoothed time series is called double-exponential smoothing. It applies the process ofexponential smoothing to a time series that is

    already exponentially smoothened.This is used when trends are not stationary.

    In the case of nonlinear trends it might benecessary to extend it even to a triple-exponential smoothing. Triple ExponentialSmoothing is better at handling parabola trendsand is normally used for such data.

  • 8/8/2019 Topic 6 - Forecasting

    39/77

    Operations Management

    Double Exponential Smoothing

    What happens when there is a definitenon-stationary trend?

    A trendy clothing boutique has had the following salesover the past 6 months:

    1 2 3 4 5 6510 512 528 530 542 552

    48 0

    49 0

    50 0

    51 0

    52 0

    53 0

    54 0

    55 0

    56 0

    1 2 3 4 5 6 7 8 9 10

    Month

    Demand

    Actual

    Forecast

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    40/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru40

    Deseasoning Demand: Seasonal Index

    Seasonal index represents the extent of seasonalinfluence for a particular segment of the year. Thecalculation involves a comparison of the expectedvalues of that period to the grand mean.The formula for computing seasonal factors is:

    Si = Di/D,where:

    Si = the seasonal index for i th period,

    Di= the average values of i th period,

    D = grand average,

    i = the ith seasonal period of the cycle

  • 8/8/2019 Topic 6 - Forecasting

    41/77

  • 8/8/2019 Topic 6 - Forecasting

    42/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Regression Analysis is a

    method of predicting the value

    of one variable based on the

    value of other variables.

    It reflects the casual

    relationship underlying the

    demand being forecast and an

    independent variable.

    RegressionAnalysis

  • 8/8/2019 Topic 6 - Forecasting

    43/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Regression analysis is of two

    types:

    (a)Simple Linear Regression: A

    regression using only one predictor iscalled a simple regression, and

    (b)Multiple Regressions: Where thereare two or more predictors, multiple

    regression analysis is employed.

    There are two types of variables,

    one that is being forecasted and

    one from which the forecast is

    made.

    The first one is known as thedependent variable, the latter asthe independent variable.

    RegressionAnalysis

  • 8/8/2019 Topic 6 - Forecasting

    44/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Where:

    yt is the dependent variable

    a is the Y interceptb is the slope of the line, and

    x is the time period

    Simple Regression Analysis

    The functional relationship between the two canbe visualized within a system of coordinates

    where the dependent variable is shown on the y

    and independent variable on the x-axis.

    yt=f(x) or yt = a + bx

  • 8/8/2019 Topic 6 - Forecasting

    45/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru45

    yt = a + bx

    0 1 2 3 4 5 x (Time)

    Y

    The simple linear regression

    model seeks to fit a linethrough various data over

    time

    The simple linear regression

    model seeks to fit a linethrough various data over

    time

    Is the linear regression modelIs the linear regression model

    a

    Yt is the regressed forecast value or dependent variable inthe model, a is the intercept value of the the regression

    line, and b is similar to the slope of the regression line.However, since it is calculated with the variability of thedata in mind, its formulation is not as straight forward asour usual notion of slope.

  • 8/8/2019 Topic 6 - Forecasting

    46/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 46

    Simple Linear Regression FormulasFor Calculating a and b

    a = y - b x

    b =xy- n(y)(x)

    x - n(x2 2

    )

  • 8/8/2019 Topic 6 - Forecasting

    47/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 47

    Problem

    Week Sales

    1 150

    2 157

    3 1624 166

    5 177

    Question: Given the data below, what is the simple linearregression model that can be used to predict sales infuture weeks?

    Question: Given the data below, what is the simple linearregression model that can be used to predict sales infuture weeks?

    A Fi t i th li i f l48

  • 8/8/2019 Topic 6 - Forecasting

    48/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 48

    Week Week*Week Sales Week*Sales

    1 1 150 1502 4 157 314

    3 9 162 486

    4 16 166 664

    5 25 177 885

    3 55 162.4 2499

    Average Sum Average Sum

    b = xy - n( y)(x)x - n(x

    = 2499 - 5(162.4)(3 ) =

    a = y - bx =162.4 - (6.3)(3) =

    2 2 =

    ) ( )55 5 96310

    6.3

    143.5

    Answer: First, using the linear regression formulas, wecan compute a and b

    Answer: First, using the linear regression formulas, wecan compute a and b

    49

  • 8/8/2019 Topic 6 - Forecasting

    49/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 49

    yt = 143.5 + 6.3x

    180

    Period

    135140145

    150

    155

    160

    165

    170

    175

    1 2 3 4 5

    Sa

    les Sales

    Forecast

    The resulting regressionmodel is:

    Now if we plot the regression generated forecasts

    against the actual sales we obtain the following chart:

  • 8/8/2019 Topic 6 - Forecasting

    50/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    r = 1 -S

    S

    xy

    2

    2

    y

    Correlation Analysis

    Mathematically, correlation coefficient is defined by:

    Where:Syx

    2 is the standard error of the estimated regression

    equation of the y values on x, and

    Sy2 is the standard error for the y values

    Correlation analysis measures the degree of relationshipbetween normally distributed dependent and

    independent variables and is signified by the correlation

    coefficient r.

  • 8/8/2019 Topic 6 - Forecasting

    51/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Multiple Regression

    With multiple regressions, we can use more than onepredictor.

    The forecast takes the form:

    Y = 0 + 1X1 + 2X2 + . . .+ nXn,

    Where:

    0 is the intercept, and

    1, 2, . . . n are coefficients

    representing the contributionof the independent variables

    X1, X2,..., Xn.

  • 8/8/2019 Topic 6 - Forecasting

    52/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    All forecasts have errors.

    However, the error in a

    forecast should be within

    confidence limits.

    The error can be measured

    by or described by the

    standard error, the meanabsolute deviation, or the

    variance.

    ForecastingErrors

  • 8/8/2019 Topic 6 - Forecasting

    53/77

    Operations Management

    Forecast AccuracySource of forecast errors:

    Model may be inadequate

    Irregular variations Incorrect use of forecasting

    technique

    Random variation

    Key to validity is randomness Accurate models: random

    errors

    Invalid models: nonrandom

    errors

    Key question: How to determine if

    forecasting errors are random?

    Prof. Upendra KachruProf. Upendra Kachru

    Forecasting

    Errors

  • 8/8/2019 Topic 6 - Forecasting

    54/77

    Operations Management

    Error measuresError - difference between actual

    value and predicted value

    Mean Absolute Deviation(MAD) - Average absolute

    error Mean Squared Error (MSE) -Average of squared error

    Mean Absolute PercentError (MAPE) - Averageabsolute percent error

    Prof. Upendra KachruProf. Upendra Kachru

    ErrorMeasurements

  • 8/8/2019 Topic 6 - Forecasting

    55/77

    Operations Management

    MAD =Actual forecast

    n

    MSE = Actual forecast)

    -1

    2

    n

    (

    Actual Forecast 100Actual

    MAPEn

    =

    Prof. Upendra KachruProf. Upendra Kachru

    Forecasting Error Formulae

    MAD Ch t i ti

  • 8/8/2019 Topic 6 - Forecasting

    56/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 56

    1 M A D 0.8 standard deviation

    1 standarddeviation 1.25 M AD

    The ideal MAD is zero which would mean there is no

    forecasting error

    When the error is less than three standard deviations, itis considered as an acceptable forecast.

    = (/2) x MAD 1.25 MAD

    Where is the standard deviation

    The larger the MAD, the less the accurate the resultingmodel

    MAD Characteristics

  • 8/8/2019 Topic 6 - Forecasting

    57/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 57

    MAD Problem (1)

    Month Sales Forecast

    1 220 n/a

    2 250 255

    3 210 205

    4 300 320

    5 325 315

    Question: What is the MAD value given theforecast values in the table below?Question: What is the MAD value given theforecast values in the table below?

  • 8/8/2019 Topic 6 - Forecasting

    58/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Solution

    MAD =

    A - F

    n=

    40

    4= 10

    t tt=1

    n

    Month Sales Forecast Abs Error 1 220 n/a

    2 250 255 5

    3 210 205 5

    4 300 320 20

    5 325 315 10

    40

    Note that by itself, the MADonly lets us know the meanerror in a set of forecasts

    Note that by itself, the MADonly lets us know the meanerror in a set of forecasts

    = 1.25 MAD = 12.5; 3 =37.5

    All readings are within limits

  • 8/8/2019 Topic 6 - Forecasting

    59/77

    Operations Management

    Example (2)

    P erio d Actual Forecast (A-F) |A-F| (A-F)^2 (|A-F|/Actual )*1

    1 217 215 2 2 4 0.

    2 213 216 -3 3 9 1.

    3 216 215 1 1 1 0.

    4 210 214 -4 4 16 1.

    5 213 211 2 2 4 0.

    6 219 214 5 5 25 2.

    7 216 217 -1 1 1 0.

    8 212 216 -4 4 16 1.

    -2 22 76 10.

    MAD= 2.75

    MSE= 10.86

    MAPE= 1.28

    MAD = 22/8 = 2.75

    MSE = 76/7 = 10.86

    MAPE = 10.26/8 =10.86

    Prof. Upendra KachruProf. Upendra Kachru

    T ki Si l

  • 8/8/2019 Topic 6 - Forecasting

    60/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru 60

    Tracking Signals

    Depending on the number of MADs selected, the TS can be used like a quality control chartindicating when the model is generating too much error in its forecasts.

    The TS formula is:

    The Tracking Signal or TS is a measure

    that indicates whether the forecastaverage is keeping pace with anygenuine upward or downward changesin demand.

    MAD

    demand)Forecast-demand(Actualn

    1

    i=i

  • 8/8/2019 Topic 6 - Forecasting

    61/77

    Operations Management

    Control Charts

    A control chart is: A visual tool for monitoring forecast errors

    Used to detect non-randomness in errors

    Forecasting errors are in control if All errors are within the control limits

    No patterns, such as trends or cycles, are present

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    62/77

    Operations Management

    Controlling the forecast

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    63/77

    Operations Management

    Control charts

    Control charts are based on the following assumptions: when errors are random, they are Normally distributed

    around a mean of zero.

    Standard deviation of error is

    95.5% of data in a normal distribution is within 2 standard

    deviation of the mean

    99.7% of data in a normal distribution is within 3 standard

    deviation of the mean

    Upper and lower control limits are often determine via

    MSE

    0 2 0 3MSE or MSE

    Prof. Upendra KachruProf. Upendra Kachru

    E l

  • 8/8/2019 Topic 6 - Forecasting

    64/77

    Operations Management

    Example

    Compute 2s control limits forforecast errors to determine ifthe forecast is accurate.

    -6.59

    -4.59

    -2.59

    -0.59

    1.41

    3.41

    5.41

    0 10

    3.295

    2 6.59

    s MSE

    s

    = =

    =

    Prof. Upendra KachruProf. Upendra Kachru

    Errors are all

    between -6.59 and

    +6.59No pattern is

    observed

    Therefore,

    according to

    control chartcriterion, forecast

    is reliable

    (Refer Slide 42)

  • 8/8/2019 Topic 6 - Forecasting

    65/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    CPFR is forecasting based on

    the concept of supply chain

    management. It is a business

    model that takes a holistic

    approach to supply chain

    management and information

    exchange among tradingpartners.

    It uses common metrics,

    standard language, and firm

    agreements to improve supplychain efficiencies for all

    participants.

    CollaborativePlanning

    Forecasting andReplenishment(CPFR)

  • 8/8/2019 Topic 6 - Forecasting

    66/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    In other words, CPFR isbased on considering the

    entire supply chain orpartnerships as a single unitand the sharing of informationbetween the links in the chain.

    The objective is to

    collectively, as members ofthe supply chain, meet theneeds of the final consumer.

    This is accomplished bysupplying the right product atthe right place, right time andright price to the customer.

    CollaborativePlanning

    Forecasting andReplenishment(CPFR)

  • 8/8/2019 Topic 6 - Forecasting

    67/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    CPFR usually begins with identifying a forecasting

    champion. The forecasting champion can be it a single

    person, a department, or a firm.

    A forecast collaboration group is formed with each organization

    choosing its member in this group. Group members shouldrepresent a variety of functional areas including sales,

    marketing, logistics/operations, finance, and information

    systems.

  • 8/8/2019 Topic 6 - Forecasting

    68/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    69/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    The driving premise of CPFR is

    that all supply chain participants

    develop a synchronized forecast.A company can collaborate with

    numerous other supply network

    members both upstream and

    downstream in the supply

    network.

    Every participant in a CPFR

    process supplier,

    manufacturer, distributor, retailer

    can view and amend forecastdata to optimize the process from

    end to end.

    CollaborativePlanning

    Forecasting andReplenishment(CPFR)

  • 8/8/2019 Topic 6 - Forecasting

    70/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Special Long-Term ForecastMethodologies

    1. Identify and analyze the

    organizational issues that

    will provide the decisionfocus

    2. Specify the key decision

    factors

    3. Identify and analyze the keyenvironmental forces

    4. Establish the scenario logics

    5. Select and elaborate the

    scenario6. Interpret the scenario for

    their decision implications

    ScenarioPlanning

  • 8/8/2019 Topic 6 - Forecasting

    71/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

    Qualitativeapproach

    (Judgmental)

    Historical Analogy

    Method

    Executive Opinion

    Method

    Survey Methods

    The Delphi Method

  • 8/8/2019 Topic 6 - Forecasting

    72/77

    Operations Management

    Usually based on judgmentsUsually based on judgmentsabout causal factors thatabout causal factors that

    underlie the demand ofunderlie the demand of

    particular products or servicesparticular products or services

    Do not require a demandDo not require a demand

    history for the product orhistory for the product orservice, therefore are usefulservice, therefore are useful

    for new products/servicesfor new products/services

    Approaches vary inApproaches vary in

    sophistication fromsophistication from

    scientifically conductedscientifically conducted

    surveys to intuitive hunchessurveys to intuitive hunches

    about future eventsabout future events

    Qualitative ApproachesQualitative Approaches

  • 8/8/2019 Topic 6 - Forecasting

    73/77

    Operations Management

    Executive Opinion MethodExecutive Opinion Method

    TechniqueTechnique Low SalesLow Sales High SalesHigh Sales

    ManagersManagersOpinionOpinion

    40.7%40.7% 39.6%39.6%

    ExecutivesExecutivesOpinionOpinion

    40.7%40.7% 41.6%41.6%

    Sales ForceSales ForceCompositeComposite

    29.6%29.6% 35.4%35.4%

    Number inNumber in

    SampleSample

    2727 4848

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    74/77

    Operations Management

    How to choose the right Tool

    Prof. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    75/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    76/77

    Operations ManagementProf. Upendra KachruProf. Upendra Kachru

  • 8/8/2019 Topic 6 - Forecasting

    77/77

    Operations

    Management

    Click to edit company slogan .