{"id":151,"date":"2018-10-12T11:43:09","date_gmt":"2018-10-12T11:43:09","guid":{"rendered":"http:\/\/mgmtp04.epgpbooks.inflibnet.ac.in\/?post_type=chapter&p=151"},"modified":"2018-10-15T07:36:16","modified_gmt":"2018-10-15T07:36:16","slug":"forecasting-demand-characteristics","status":"publish","type":"chapter","link":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/chapter\/forecasting-demand-characteristics\/","title":{"rendered":"Forecasting: Demand Characteristics"},"content":{"raw":"
\r\n\r\n \r\n

Learning Objectives:<\/span><\/strong><\/p>\r\n \r\n

The Learning objectives of the module are to address the following questions:<\/span><\/p>\r\n\r\n<\/div>\r\n

\r\n\r\n \r\n\r\n1.\u00a0 Understand the role of forecasting for both an enterprise and a supply chain.\r\n\r\n2.\u00a0 To Identify the components of a demand forecast.\r\n\r\n3.\u00a0 Forecast demand in a supply chain given historical demand data using time-series methodologies.\r\n\r\n4.\u00a0 How to analyze demand forecasts to estimate forecast error.\r\n\r\n \r\n\r\nBasic Approach of Learning:\u00a0<\/span><\/strong>\r\n
    \r\n \t
  • Understand the objective of forecasting.<\/span><\/li>\r\n \t
  • Integrate demand planning and forecasting throughout the supply chain.<\/li>\r\n \t
  • Identify the major factors that influence the demand forecast.<\/li>\r\n \t
  • Forecast at the appropriate level of aggregation.<\/li>\r\n \t
  • Establish performance and error measures for the forecast.<\/li>\r\n<\/ul>\r\n<\/div>\r\n
    \r\n\r\n \r\n\r\nIntroduction:\u00a0<\/strong>\r\n\r\n \r\n

    Demand forecasts form the basis of operations across the organization. Demand\/ Supply are based on the anticipation of customer demand. For Demand anticipation, operations manager must plan the level of activity (viz. production, inventory, logistics\/transportation etc, but not the actual amount to be executed.<\/p>\r\n \r\n

    For a Burger paint store, orders the base paint \/ dyes anticipating possible orders from customers, although it performs final mixing of the paints in response to actual orders. The paint store uses a forecast of demand to determine the quantity of paint\/ dyes to have at store\/ site. The paint\/ dyes factory that produces the base, also require to forecasts to determine its own production\/ inventory levels. The Suppliers at end of paint factors also need forecasts. Therefore in every stage of supply, own separate forecast is needed to be maintained, these forecasts are often very different. The result may be a mismatch between supply and demand.<\/p>\r\n \r\n

    For more accuracy, all stages of supply chain need to produce a collaborative forecast so that customers can be served in an effective manner. Firms from FMCG to electronic manufactures have improved their supply-demand gap by moving towards collaborative forecasting.<\/p>\r\n \r\n\r\n2.\u00a0 <\/b><\/span>Characteristics<\/b>\u00a0of Forecasting\u00a0<\/b><\/span><\/span>\r\n\r\n \r\n

    Operation managers should be well-versed with the characteristics of forecasting, including:<\/span><\/p>\r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n

    a) Forecasts are inaccurate and include both the expected value of the forecast and a measure of forecast error.Example: To understand the importance of forecast error, consider two motorbike dealers. One of them expects sales to range between 100 and 1,900 units, whereas the other expects sales to range between 900 and 1,100 units. Even though both dealers anticipate average sales of 1,000, the sourcing policies for each dealer should be very different, given the difference in forecast accuracy. Thus, the forecast error (or demand uncertainty) is a key input into most supply chain decisions.<\/p>\r\n \r\n\r\nIn practice, very less firms\u2019 estimates forecast error.\r\n\r\n \r\n

    b) Long-term forecasts are less accurate than short-term forecasts; that is, long-term forecasts have a larger standard deviation of error relative to the mean than short- term forecasts.Example: Tata Motors has improved its performance while focusing on short-term forecasts. The company has instituted a replenishment process that enables it to respond to an order within hours. For example, if a store manager places an order by 10 a.m., the order is delivered by 7 p.m. the same day. Therefore, the manager has to forecast what will sell that night only less than 12 hours before the actual sale. The short lead time allows a manager to take into account current information that could affect product sales, such as the weather. This forecast is likely to be more accurate than if the store manager had to forecast demand a week in advance.<\/p>\r\n \r\n

    c) Aggregate forecasts are more accurate than individual unit forecasts, as they tend to have a smaller standard deviation of error relative to the mean.Example: GDP of India for given year can be easily evaluated, with less than a 2 percent error. However, it is a bit difficult to forecast yearly revenue for a company with less than a 2 percent error, and it is even harder to forecast revenue for a given product with the same degree of accuracy.<\/p>\r\n \r\n\r\n3. Forecasting: Components and Methods\u00a0<\/span><\/strong>\r\n\r\n \r\n\r\nAn effective forecasting requires the knowledge of the following:<\/span>\r\n\r\n \r\n\r\na)\u00a0\u00a0\u00a0 Demand from recent past<\/span>\r\n\r\nb)\u00a0\u00a0\u00a0 Lead time of product replenishment;<\/span>\r\n\r\nc)\u00a0\u00a0\u00a0 Planned advertising or marketing efforts;<\/span>\r\n\r\nd)\u00a0\u00a0\u00a0 Planned price discounts;<\/span>\r\n\r\ne)\u00a0\u00a0\u00a0 Present State of the economy;<\/span>\r\n\r\nf)\u00a0\u00a0\u00a0\u00a0 Competitive positioning.<\/span>\r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n

    For example, historically a Gift items shop may have experienced low demand for Gift items during non-festival seasons and high demand in Festival seasons (Deepawali, Xmas, New Year etc.). If the firm decides to discount the product during the off-seasons, the situation is likely to change, with some of the future demand shifting during off-season times. The firm should make its forecast taking this factor into consideration.<\/p>\r\n \r\n\r\n3.1. Types of forecasting methods:\u00a0<\/strong>\r\n\r\n \r\n

    Theoretically, Forecasting methods are classified according to the following four types:<\/p>\r\n \r\n

    a<\/em><\/strong>. Qualitative Forecasting methods: <\/em><\/strong>Appropriate when historical data are available.<\/p>\r\n \r\n

    b.\u00a0<\/em><\/strong>Time series forecasting methods: <\/em><\/strong>Use historical demand to make a forecast. It is among most appropriate method, when the basic demand pattern does not vary significantly from one year to the next.<\/p>\r\n \r\n

    c.\u00a0<\/em><\/strong>Casual Forecasting Methods: <\/em><\/strong>Forecasting methods assume that the demand forecast is highly correlated with certain factors in the environment (the state of the economy, interest rates, etc.).<\/p>\r\n \r\n\r\nd<\/em><\/strong>. Simulation Methods<\/em><\/strong>: Simulation forecasting methods focused on ascertaining demand based on various underlined factors including price, impact of competition etc.\r\n\r\n \r\n

    Components \u00a0of \u00a0an \u00a0Observation \u00a0in \u00a0the \u00a0forecasting \u00a0methods \u00a0includes- \u00a0(a) \u00a0systematic component (expected \u00a0value \u00a0of \u00a0demand); \u00a0whereas, \u00a0expected \u00a0value \u00a0of \u00a0demand \u00a0could \u00a0be effected by \u00a0Level (current de-seasonalized demand), Trend (Growth or decline in demand)\u00a0and seasonality (predictable seasonal fluctuation); (b) Random component (part of forecast\u00a0<\/span>that deviates from systematic component); (c). Forecast error (difference between forecast and actual demand).<\/span><\/p>\r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n\r\n4. Time series forecasting methods\u00a0<\/strong>\r\n\r\n \r\n\r\nThe equation for calculating the systematic component may take a variety of forms:\r\n\r\n \r\n\r\na)\u00a0M<\/em><\/strong>ultiplicative: <\/em><\/strong>Systematic component = level * trend * seasonal factor\r\n\r\n \r\n\r\nb)\u00a0Additive: <\/em><\/strong>Systematic component = level + trend + seasonal factor\r\n\r\n \r\n\r\nc)\u00a0M<\/em><\/strong>ixed: <\/em><\/strong>Systematic component = 1level + trend2 * seasonal factor\r\n\r\n \r\n

    The specific form of the systematic component applicable to a given forecast depends on the nature of demand.<\/p>\r\n \r\n\r\n4.1 Static Methods\u00a0<\/strong>\r\n\r\n \r\n

    A static method assumes that the estimates of level, trend, and seasonality within the systematic component do not vary as new demand is observed. In this case, we estimate each of these parameters based on historical data and then use the same values for all future forecasts. Systematic component of demand is mixed; that is,<\/p>\r\n \r\n\r\nSystematic component = 1level + trend2 * seasonal factor<\/em>\r\n\r\n \r\n\r\nS<\/em>t <\/em>= estimate of seasonal factor for Period t <\/em>\r\n\r\nD<\/em>t <\/em>= actual demand observed in Period t<\/em>\r\n\r\nF<\/em>t <\/em>= forecast of demand for Period t<\/em>\r\n\r\n \r\n

    In a static forecasting method, the forecast in Period t <\/em>for demand in Period t <\/em>+ l <\/em>is a product of the level in Period t <\/em>+ l <\/em>and the seasonal factor for Period t <\/em>+ l. <\/em>The level in Period t <\/em>+ l <\/em>is the sum of the level in Period 0 (L<\/em>) and (t <\/em>+ l<\/em>) times the trend T. <\/em>The forecast in Period t <\/em>for demand in Period t <\/em>+ l <\/em>is thus given as<\/p>\r\n \r\n\r\nFt <\/em>+ l <\/em>= 3L <\/em>+ 1t <\/em>+ l<\/em>2T<\/em>4St <\/em>+ l <\/em>(7.1)<\/strong>\r\n\r\n \r\n

    We now describe one method for estimating the three parameters L<\/em>, T<\/em>, and S.<\/em><\/p>\r\n \r\n

    Let\u2019s take an example of salt producing firm called Tata Salt, Quarterly retail demand data for\u00a0<\/span>the past three years are shown in Table I \u00a0and Figure 1-1 as follows:<\/span><\/p>\r\n\r\n<\/div>\r\n

    \r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
    Year<\/strong><\/td>\r\nQuart er<\/strong><\/td>\r\nPeriod, t<\/em><\/strong><\/td>\r\nDemand, D<\/em><\/strong>t<\/em><\/strong><\/td>\r\n<\/tr>\r\n
    1<\/strong><\/td>\r\n2<\/strong><\/td>\r\n1<\/strong><\/td>\r\n8,000<\/strong><\/td>\r\n<\/tr>\r\n
    1<\/strong><\/td>\r\n3<\/strong><\/td>\r\n2<\/strong><\/td>\r\n13,000<\/strong><\/td>\r\n<\/tr>\r\n
    1<\/strong><\/td>\r\n4<\/strong><\/td>\r\n3<\/strong><\/td>\r\n23,000<\/strong><\/td>\r\n<\/tr>\r\n
    2<\/strong><\/td>\r\n1<\/strong><\/td>\r\n4<\/strong><\/td>\r\n34,000<\/strong><\/td>\r\n<\/tr>\r\n
    2<\/strong><\/td>\r\n2<\/strong><\/td>\r\n5<\/strong><\/td>\r\n10,000<\/strong><\/td>\r\n<\/tr>\r\n
    2<\/strong><\/td>\r\n3<\/strong><\/td>\r\n6<\/strong><\/td>\r\n18,000<\/strong><\/td>\r\n<\/tr>\r\n
    2<\/strong><\/td>\r\n4<\/strong><\/td>\r\n7<\/strong><\/td>\r\n23,000<\/strong><\/td>\r\n<\/tr>\r\n
    3<\/strong><\/td>\r\n1<\/strong><\/td>\r\n8<\/strong><\/td>\r\n38,000<\/strong><\/td>\r\n<\/tr>\r\n
    3<\/strong><\/td>\r\n2<\/strong><\/td>\r\n9<\/strong><\/td>\r\n12,000<\/strong><\/td>\r\n<\/tr>\r\n
    3<\/strong><\/td>\r\n3<\/strong><\/td>\r\n10<\/strong><\/td>\r\n13,000<\/strong><\/td>\r\n<\/tr>\r\n
    3<\/strong><\/td>\r\n4<\/strong><\/td>\r\n11<\/strong><\/td>\r\n32,000<\/strong><\/td>\r\n<\/tr>\r\n
    4<\/strong><\/td>\r\n1<\/strong><\/td>\r\n12<\/strong><\/td>\r\n41,000<\/strong><\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n<\/div>\r\n\"\"\r\n
    \r\n

    Figure 1-1 : Quarterly demand of Tata Salt<\/strong><\/p>\r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n\r\nEstimate Level and Trend<\/strong>\r\n\r\n\"\"\r\n\r\n<\/div>\r\n
    \r\n\r\n\"\"\r\n

    A linear relationship exists between the deseasonalized demand and time based on the change in demand over time<\/span><\/p>\r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n\r\nD<\/em>t \u00a0<\/em>= L <\/em>+ T<\/em>t<\/em>\r\n\r\n \r\n\r\nEstimating Seasonal Factors\r\n\r\n \r\n

    S<\/em>1 \u00a0= (S<\/em>1 + S<\/em>5 + S<\/em>9 ) \/ 3 = (0.42 + 0.47 + 0.52) \/ 3 = 0.47<\/p>\r\n

    S<\/em>2 \u00a0= (S<\/em>2 + S<\/em>6 + S<\/em>10 ) \/ 3 = (0.67 + 0.83 + 0.55) \/ 3 = 0.68<\/p>\r\n

    S<\/em>3 \u00a0= (S<\/em>3 + S<\/em>7 \u00a0+ S<\/em>11 ) \/ 3 = (1.15 +1.04 +1.32) \/ 3 = 1.17<\/p>\r\n

    S<\/em>4 \u00a0= (S<\/em>4 + S<\/em>8 + S<\/em>12 ) \/ 3 = (1.66 +1.68 +1.66) \/ 3 = 1.67<\/p>\r\n \r\n\r\n\"\"\r\n\r\n \r\n\r\n<\/div>\r\n

    \r\n\r\n \r\n\r\n \r\n\r\n \r\n\r\nF<\/em>13 \u00a0= (L <\/em>+13T <\/em>)S<\/em>13 \u00a0= (18,439 +13\u00b4 524)0.47 = 11,868\r\n\r\nF<\/em>14 = (L <\/em>+14T <\/em>)S<\/em>14 = (18,439 +14 \u00b4 524)0.68 = 17,527\r\n\r\nF<\/em>15 = (L <\/em>+15T <\/em>)S<\/em>15 = (18,439 +15\u00b4 524)1.17 = 30,770\r\n\r\nF<\/em>16 \u00a0= (L <\/em>+16T <\/em>)S<\/em>16 \u00a0= (18,439 +16 \u00b4 524)1.67 = 44,794\r\n\r\n \r\n\r\n4.2 Adaptive Forecasting<\/strong>\r\n\r\n \r\n

    In adaptive forecasting, the estimates of level, trend, and seasonality are updated after each demand observation. The main advantage of adaptive forecasting is that estimates incorporate all new data that are observed. We now discuss a basic framework and several methods that can be used for this type of forecast. The framework is provided in the most general setting, when the systematic component of demand data has the mixed form and contains a level, a trend, and a seasonal factor. It can easily be modified for the other two cases, however. The framework can also be specialized for the case in which the systematic component contains no seasonality or trend. We assume that we have a set of historical data for n <\/em>periods and that demand is seasonal, with periodicity p. <\/em>Given quarterly data, wherein the pattern repeats itself every year, we have a periodicity of p <\/em>= 4.<\/p>\r\n \r\n\r\nWe begin by defining a few terms:\r\n\r\n \r\n

    Lt <\/em>= estimate of level at the end of Period t <\/em><\/p>\r\n

    Tt <\/em>= estimate of trend at the end of Period t <\/em><\/p>\r\n

    St <\/em>= estimate of seasonal factor for Period t<\/em><\/p>\r\n

    Ft <\/em>= forecast of demand for Period t <\/em>(made in Period t <\/em>\u2212 1 or earlier)<\/p>\r\n

    Dt <\/em>= actual demand observed in Period t <\/em><\/p>\r\n

    Et <\/em>= Ft \u2212 Dt <\/em>= forecast error in Period t<\/em><\/p>\r\n \r\n\r\nDiscussion<\/strong>\r\n\r\n \r\n

    The overall demand characteristics of Forecasting that can help firm to achieve business excellence includes<\/p>\r\n\r\n<\/div>\r\n

      \r\n \t
    1. Understand the role of forecasting for both an enterprise and a supply chain. <\/em><\/strong>Forecasting is a key driver of virtually every design and planning decision made in both an enterprise and a supply chain. Enterprises have always forecast demand and used it to make decisions. A relatively recent phenomenon, however, is to create collaborative forecasts for an entire supply chain and use these as the basis for decisions. Collaborative forecasting greatly increases the accuracy of forecasts and allows the supply chain to maximize its performance. Without collaboration, supply chain stages farther from demand will likely have poor forecasts that will lead to supply chain inefficiencies and a lack of responsiveness.<\/li>\r\n \t
    2. Identify the components of fdema 3.<\/em><\/strong><\/li>\r\n \t
    3. I<\/em><\/strong>dentify the components of a demand forecast. <\/em><\/strong>Demand consists of a systematic and a random component. The systematic component measures the expected value of demand. The random component measures fluctuations in demand from the expected value. The systematic component consists of level, trend, and seasonality. Level measures the current deseasonalized demand. Trend measures the current rate of growth or decline in demand. Seasonality indicates predictable seasonal fluctuations in demand.<\/li>\r\n \t
    4. F<\/em><\/strong>orecast demand in a supply chain given historical demand data using time-series methodologies. <\/em><\/strong>Time-series methods for forecasting are categorized as static <\/em>or adaptive. <\/em>In static methods, the estimates of parameters and demand patterns are not updated as new demand is observed. Static methods include regression. In adaptive methods, the estimates are updated each time a new demand is observed. Adaptive methods include moving averages, simple exponential smoothing, Holt\u2019s model, and Winter\u2019s model. Moving averages and simple exponential smoothing are best used when demand displays neither trend nor seasonality. Holt\u2019s model is best when demand displays a trend but no seasonality. Winter\u2019s model is appropriate when demand displays both trend and seasonality.<\/li>\r\n \t
    5. Analyze demand forecasts to estimate forecast error. <\/em><\/strong>Forecast error measures the random component of demand. This measure is important because it reveals how inaccurate a forecast is likely to be and what contingencies a firm may have to plan for. The MSE, MAD, and MAPE are used to estimate the size of the forecast error. The bias and TS are used to estimate if the forecast consistently over- or underforecasts or if demand has deviated significantly from historical norms.<\/li>\r\n<\/ol>\r\n \r\n\r\nSuggested Readings:<\/strong>\r\n\r\n \r\n

      a) Moon(2013): Demand and Supply Integration: The Key to World-Class Demand Forecasting. FT Press Operations Management.<\/p>\r\n

      b) Anderson (2013): Operations Management For Dummies. For Dummies.<\/p>\r\n

      c) Makridakis (1998): Forecasting: Methods and Applications. John Wiley & Sons.<\/p>\r\n

      d) Munson (2011): The Supply Chain Management Casebook: Comprehensive Coverage and Best Practices in SCM. FT Press Operations Management.<\/p>\r\n

      e) Drake (2015): Advances in Business, Operations, and Product Analytics: Cutting Edge Cases from Finance to Manufacturing to Healthcare. Pearson FT Press.<\/p>\r\n

      <\/p>","rendered":"

      \n

       <\/p>\n

      Learning Objectives:<\/span><\/strong><\/p>\n

       <\/p>\n

      The Learning objectives of the module are to address the following questions:<\/span><\/p>\n<\/div>\n

      \n

       <\/p>\n

      1.\u00a0 Understand the role of forecasting for both an enterprise and a supply chain.<\/p>\n

      2.\u00a0 To Identify the components of a demand forecast.<\/p>\n

      3.\u00a0 Forecast demand in a supply chain given historical demand data using time-series methodologies.<\/p>\n

      4.\u00a0 How to analyze demand forecasts to estimate forecast error.<\/p>\n

       <\/p>\n

      Basic Approach of Learning:\u00a0<\/span><\/strong><\/p>\n

        \n
      • Understand the objective of forecasting.<\/span><\/li>\n
      • Integrate demand planning and forecasting throughout the supply chain.<\/li>\n
      • Identify the major factors that influence the demand forecast.<\/li>\n
      • Forecast at the appropriate level of aggregation.<\/li>\n
      • Establish performance and error measures for the forecast.<\/li>\n<\/ul>\n<\/div>\n
        \n

         <\/p>\n

        Introduction:\u00a0<\/strong><\/p>\n

         <\/p>\n

        Demand forecasts form the basis of operations across the organization. Demand\/ Supply are based on the anticipation of customer demand. For Demand anticipation, operations manager must plan the level of activity (viz. production, inventory, logistics\/transportation etc, but not the actual amount to be executed.<\/p>\n

         <\/p>\n

        For a Burger paint store, orders the base paint \/ dyes anticipating possible orders from customers, although it performs final mixing of the paints in response to actual orders. The paint store uses a forecast of demand to determine the quantity of paint\/ dyes to have at store\/ site. The paint\/ dyes factory that produces the base, also require to forecasts to determine its own production\/ inventory levels. The Suppliers at end of paint factors also need forecasts. Therefore in every stage of supply, own separate forecast is needed to be maintained, these forecasts are often very different. The result may be a mismatch between supply and demand.<\/p>\n

         <\/p>\n

        For more accuracy, all stages of supply chain need to produce a collaborative forecast so that customers can be served in an effective manner. Firms from FMCG to electronic manufactures have improved their supply-demand gap by moving towards collaborative forecasting.<\/p>\n

         <\/p>\n

        2.\u00a0 <\/b><\/span>Characteristics<\/b>\u00a0of Forecasting\u00a0<\/b><\/span><\/span><\/p>\n

         <\/p>\n

        Operation managers should be well-versed with the characteristics of forecasting, including:<\/span><\/p>\n<\/div>\n

        \n

         <\/p>\n

        a) Forecasts are inaccurate and include both the expected value of the forecast and a measure of forecast error.Example: To understand the importance of forecast error, consider two motorbike dealers. One of them expects sales to range between 100 and 1,900 units, whereas the other expects sales to range between 900 and 1,100 units. Even though both dealers anticipate average sales of 1,000, the sourcing policies for each dealer should be very different, given the difference in forecast accuracy. Thus, the forecast error (or demand uncertainty) is a key input into most supply chain decisions.<\/p>\n

         <\/p>\n

        In practice, very less firms\u2019 estimates forecast error.<\/p>\n

         <\/p>\n

        b) Long-term forecasts are less accurate than short-term forecasts; that is, long-term forecasts have a larger standard deviation of error relative to the mean than short- term forecasts.Example: Tata Motors has improved its performance while focusing on short-term forecasts. The company has instituted a replenishment process that enables it to respond to an order within hours. For example, if a store manager places an order by 10 a.m., the order is delivered by 7 p.m. the same day. Therefore, the manager has to forecast what will sell that night only less than 12 hours before the actual sale. The short lead time allows a manager to take into account current information that could affect product sales, such as the weather. This forecast is likely to be more accurate than if the store manager had to forecast demand a week in advance.<\/p>\n

         <\/p>\n

        c) Aggregate forecasts are more accurate than individual unit forecasts, as they tend to have a smaller standard deviation of error relative to the mean.Example: GDP of India for given year can be easily evaluated, with less than a 2 percent error. However, it is a bit difficult to forecast yearly revenue for a company with less than a 2 percent error, and it is even harder to forecast revenue for a given product with the same degree of accuracy.<\/p>\n

         <\/p>\n

        3. Forecasting: Components and Methods\u00a0<\/span><\/strong><\/p>\n

         <\/p>\n

        An effective forecasting requires the knowledge of the following:<\/span><\/p>\n

         <\/p>\n

        a)\u00a0\u00a0\u00a0 Demand from recent past<\/span><\/p>\n

        b)\u00a0\u00a0\u00a0 Lead time of product replenishment;<\/span><\/p>\n

        c)\u00a0\u00a0\u00a0 Planned advertising or marketing efforts;<\/span><\/p>\n

        d)\u00a0\u00a0\u00a0 Planned price discounts;<\/span><\/p>\n

        e)\u00a0\u00a0\u00a0 Present State of the economy;<\/span><\/p>\n

        f)\u00a0\u00a0\u00a0\u00a0 Competitive positioning.<\/span><\/p>\n<\/div>\n

        \n

         <\/p>\n

        For example, historically a Gift items shop may have experienced low demand for Gift items during non-festival seasons and high demand in Festival seasons (Deepawali, Xmas, New Year etc.). If the firm decides to discount the product during the off-seasons, the situation is likely to change, with some of the future demand shifting during off-season times. The firm should make its forecast taking this factor into consideration.<\/p>\n

         <\/p>\n

        3.1. Types of forecasting methods:\u00a0<\/strong><\/p>\n

         <\/p>\n

        Theoretically, Forecasting methods are classified according to the following four types:<\/p>\n

         <\/p>\n

        a<\/em><\/strong>. Qualitative Forecasting methods: <\/em><\/strong>Appropriate when historical data are available.<\/p>\n

         <\/p>\n

        b.\u00a0<\/em><\/strong>Time series forecasting methods: <\/em><\/strong>Use historical demand to make a forecast. It is among most appropriate method, when the basic demand pattern does not vary significantly from one year to the next.<\/p>\n

         <\/p>\n

        c.\u00a0<\/em><\/strong>Casual Forecasting Methods: <\/em><\/strong>Forecasting methods assume that the demand forecast is highly correlated with certain factors in the environment (the state of the economy, interest rates, etc.).<\/p>\n

         <\/p>\n

        d<\/em><\/strong>. Simulation Methods<\/em><\/strong>: Simulation forecasting methods focused on ascertaining demand based on various underlined factors including price, impact of competition etc.<\/p>\n

         <\/p>\n

        Components \u00a0of \u00a0an \u00a0Observation \u00a0in \u00a0the \u00a0forecasting \u00a0methods \u00a0includes- \u00a0(a) \u00a0systematic component (expected \u00a0value \u00a0of \u00a0demand); \u00a0whereas, \u00a0expected \u00a0value \u00a0of \u00a0demand \u00a0could \u00a0be effected by \u00a0Level (current de-seasonalized demand), Trend (Growth or decline in demand)\u00a0and seasonality (predictable seasonal fluctuation); (b) Random component (part of forecast\u00a0<\/span>that deviates from systematic component); (c). Forecast error (difference between forecast and actual demand).<\/span><\/p>\n<\/div>\n

        \n

         <\/p>\n

        4. Time series forecasting methods\u00a0<\/strong><\/p>\n

         <\/p>\n

        The equation for calculating the systematic component may take a variety of forms:<\/p>\n

         <\/p>\n

        a)\u00a0M<\/em><\/strong>ultiplicative: <\/em><\/strong>Systematic component = level * trend * seasonal factor<\/p>\n

         <\/p>\n

        b)\u00a0Additive: <\/em><\/strong>Systematic component = level + trend + seasonal factor<\/p>\n

         <\/p>\n

        c)\u00a0M<\/em><\/strong>ixed: <\/em><\/strong>Systematic component = 1level + trend2 * seasonal factor<\/p>\n

         <\/p>\n

        The specific form of the systematic component applicable to a given forecast depends on the nature of demand.<\/p>\n

         <\/p>\n

        4.1 Static Methods\u00a0<\/strong><\/p>\n

         <\/p>\n

        A static method assumes that the estimates of level, trend, and seasonality within the systematic component do not vary as new demand is observed. In this case, we estimate each of these parameters based on historical data and then use the same values for all future forecasts. Systematic component of demand is mixed; that is,<\/p>\n

         <\/p>\n

        Systematic component = 1level + trend2 * seasonal factor<\/em><\/p>\n

         <\/p>\n

        S<\/em>t <\/em>= estimate of seasonal factor for Period t <\/em><\/p>\n

        D<\/em>t <\/em>= actual demand observed in Period t<\/em><\/p>\n

        F<\/em>t <\/em>= forecast of demand for Period t<\/em><\/p>\n

         <\/p>\n

        In a static forecasting method, the forecast in Period t <\/em>for demand in Period t <\/em>+ l <\/em>is a product of the level in Period t <\/em>+ l <\/em>and the seasonal factor for Period t <\/em>+ l. <\/em>The level in Period t <\/em>+ l <\/em>is the sum of the level in Period 0 (L<\/em>) and (t <\/em>+ l<\/em>) times the trend T. <\/em>The forecast in Period t <\/em>for demand in Period t <\/em>+ l <\/em>is thus given as<\/p>\n

         <\/p>\n

        Ft <\/em>+ l <\/em>= 3L <\/em>+ 1t <\/em>+ l<\/em>2T<\/em>4St <\/em>+ l <\/em>(7.1)<\/strong><\/p>\n

         <\/p>\n

        We now describe one method for estimating the three parameters L<\/em>, T<\/em>, and S.<\/em><\/p>\n

         <\/p>\n

        Let\u2019s take an example of salt producing firm called Tata Salt, Quarterly retail demand data for\u00a0<\/span>the past three years are shown in Table I \u00a0and Figure 1-1 as follows:<\/span><\/p>\n<\/div>\n

        \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
        Year<\/strong><\/td>\nQuart er<\/strong><\/td>\nPeriod, t<\/em><\/strong><\/td>\nDemand, D<\/em><\/strong>t<\/em><\/strong><\/td>\n<\/tr>\n
        1<\/strong><\/td>\n2<\/strong><\/td>\n1<\/strong><\/td>\n8,000<\/strong><\/td>\n<\/tr>\n
        1<\/strong><\/td>\n3<\/strong><\/td>\n2<\/strong><\/td>\n13,000<\/strong><\/td>\n<\/tr>\n
        1<\/strong><\/td>\n4<\/strong><\/td>\n3<\/strong><\/td>\n23,000<\/strong><\/td>\n<\/tr>\n
        2<\/strong><\/td>\n1<\/strong><\/td>\n4<\/strong><\/td>\n34,000<\/strong><\/td>\n<\/tr>\n
        2<\/strong><\/td>\n2<\/strong><\/td>\n5<\/strong><\/td>\n10,000<\/strong><\/td>\n<\/tr>\n
        2<\/strong><\/td>\n3<\/strong><\/td>\n6<\/strong><\/td>\n18,000<\/strong><\/td>\n<\/tr>\n
        2<\/strong><\/td>\n4<\/strong><\/td>\n7<\/strong><\/td>\n23,000<\/strong><\/td>\n<\/tr>\n
        3<\/strong><\/td>\n1<\/strong><\/td>\n8<\/strong><\/td>\n38,000<\/strong><\/td>\n<\/tr>\n
        3<\/strong><\/td>\n2<\/strong><\/td>\n9<\/strong><\/td>\n12,000<\/strong><\/td>\n<\/tr>\n
        3<\/strong><\/td>\n3<\/strong><\/td>\n10<\/strong><\/td>\n13,000<\/strong><\/td>\n<\/tr>\n
        3<\/strong><\/td>\n4<\/strong><\/td>\n11<\/strong><\/td>\n32,000<\/strong><\/td>\n<\/tr>\n
        4<\/strong><\/td>\n1<\/strong><\/td>\n12<\/strong><\/td>\n41,000<\/strong><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

        \"\"<\/p>\n

        \n

        Figure 1-1 : Quarterly demand of Tata Salt<\/strong><\/p>\n<\/div>\n

        \n

         <\/p>\n

        Estimate Level and Trend<\/strong><\/p>\n

        \"\"<\/p>\n<\/div>\n

        \n

        \"\"<\/p>\n

        A linear relationship exists between the deseasonalized demand and time based on the change in demand over time<\/span><\/p>\n<\/div>\n

        \n

         <\/p>\n

        D<\/em>t \u00a0<\/em>= L <\/em>+ T<\/em>t<\/em><\/p>\n

         <\/p>\n

        Estimating Seasonal Factors<\/p>\n

         <\/p>\n

        S<\/em>1 \u00a0= (S<\/em>1 + S<\/em>5 + S<\/em>9 ) \/ 3 = (0.42 + 0.47 + 0.52) \/ 3 = 0.47<\/p>\n

        S<\/em>2 \u00a0= (S<\/em>2 + S<\/em>6 + S<\/em>10 ) \/ 3 = (0.67 + 0.83 + 0.55) \/ 3 = 0.68<\/p>\n

        S<\/em>3 \u00a0= (S<\/em>3 + S<\/em>7 \u00a0+ S<\/em>11 ) \/ 3 = (1.15 +1.04 +1.32) \/ 3 = 1.17<\/p>\n

        S<\/em>4 \u00a0= (S<\/em>4 + S<\/em>8 + S<\/em>12 ) \/ 3 = (1.66 +1.68 +1.66) \/ 3 = 1.67<\/p>\n

         <\/p>\n

        \"\"<\/p>\n

         <\/p>\n<\/div>\n

        \n

         <\/p>\n

         <\/p>\n

         <\/p>\n

        F<\/em>13 \u00a0= (L <\/em>+13T <\/em>)S<\/em>13 \u00a0= (18,439 +13\u00b4 524)0.47 = 11,868<\/p>\n

        F<\/em>14 = (L <\/em>+14T <\/em>)S<\/em>14 = (18,439 +14 \u00b4 524)0.68 = 17,527<\/p>\n

        F<\/em>15 = (L <\/em>+15T <\/em>)S<\/em>15 = (18,439 +15\u00b4 524)1.17 = 30,770<\/p>\n

        F<\/em>16 \u00a0= (L <\/em>+16T <\/em>)S<\/em>16 \u00a0= (18,439 +16 \u00b4 524)1.67 = 44,794<\/p>\n

         <\/p>\n

        4.2 Adaptive Forecasting<\/strong><\/p>\n

         <\/p>\n

        In adaptive forecasting, the estimates of level, trend, and seasonality are updated after each demand observation. The main advantage of adaptive forecasting is that estimates incorporate all new data that are observed. We now discuss a basic framework and several methods that can be used for this type of forecast. The framework is provided in the most general setting, when the systematic component of demand data has the mixed form and contains a level, a trend, and a seasonal factor. It can easily be modified for the other two cases, however. The framework can also be specialized for the case in which the systematic component contains no seasonality or trend. We assume that we have a set of historical data for n <\/em>periods and that demand is seasonal, with periodicity p. <\/em>Given quarterly data, wherein the pattern repeats itself every year, we have a periodicity of p <\/em>= 4.<\/p>\n

         <\/p>\n

        We begin by defining a few terms:<\/p>\n

         <\/p>\n

        Lt <\/em>= estimate of level at the end of Period t <\/em><\/p>\n

        Tt <\/em>= estimate of trend at the end of Period t <\/em><\/p>\n

        St <\/em>= estimate of seasonal factor for Period t<\/em><\/p>\n

        Ft <\/em>= forecast of demand for Period t <\/em>(made in Period t <\/em>\u2212 1 or earlier)<\/p>\n

        Dt <\/em>= actual demand observed in Period t <\/em><\/p>\n

        Et <\/em>= Ft \u2212 Dt <\/em>= forecast error in Period t<\/em><\/p>\n

         <\/p>\n

        Discussion<\/strong><\/p>\n

         <\/p>\n

        The overall demand characteristics of Forecasting that can help firm to achieve business excellence includes<\/p>\n<\/div>\n

          \n
        1. Understand the role of forecasting for both an enterprise and a supply chain. <\/em><\/strong>Forecasting is a key driver of virtually every design and planning decision made in both an enterprise and a supply chain. Enterprises have always forecast demand and used it to make decisions. A relatively recent phenomenon, however, is to create collaborative forecasts for an entire supply chain and use these as the basis for decisions. Collaborative forecasting greatly increases the accuracy of forecasts and allows the supply chain to maximize its performance. Without collaboration, supply chain stages farther from demand will likely have poor forecasts that will lead to supply chain inefficiencies and a lack of responsiveness.<\/li>\n
        2. Identify the components of fdema 3.<\/em><\/strong><\/li>\n
        3. I<\/em><\/strong>dentify the components of a demand forecast. <\/em><\/strong>Demand consists of a systematic and a random component. The systematic component measures the expected value of demand. The random component measures fluctuations in demand from the expected value. The systematic component consists of level, trend, and seasonality. Level measures the current deseasonalized demand. Trend measures the current rate of growth or decline in demand. Seasonality indicates predictable seasonal fluctuations in demand.<\/li>\n
        4. F<\/em><\/strong>orecast demand in a supply chain given historical demand data using time-series methodologies. <\/em><\/strong>Time-series methods for forecasting are categorized as static <\/em>or adaptive. <\/em>In static methods, the estimates of parameters and demand patterns are not updated as new demand is observed. Static methods include regression. In adaptive methods, the estimates are updated each time a new demand is observed. Adaptive methods include moving averages, simple exponential smoothing, Holt\u2019s model, and Winter\u2019s model. Moving averages and simple exponential smoothing are best used when demand displays neither trend nor seasonality. Holt\u2019s model is best when demand displays a trend but no seasonality. Winter\u2019s model is appropriate when demand displays both trend and seasonality.<\/li>\n
        5. Analyze demand forecasts to estimate forecast error. <\/em><\/strong>Forecast error measures the random component of demand. This measure is important because it reveals how inaccurate a forecast is likely to be and what contingencies a firm may have to plan for. The MSE, MAD, and MAPE are used to estimate the size of the forecast error. The bias and TS are used to estimate if the forecast consistently over- or underforecasts or if demand has deviated significantly from historical norms.<\/li>\n<\/ol>\n

           <\/p>\n

          Suggested Readings:<\/strong><\/p>\n

           <\/p>\n

          a) Moon(2013): Demand and Supply Integration: The Key to World-Class Demand Forecasting. FT Press Operations Management.<\/p>\n

          b) Anderson (2013): Operations Management For Dummies. For Dummies.<\/p>\n

          c) Makridakis (1998): Forecasting: Methods and Applications. John Wiley & Sons.<\/p>\n

          d) Munson (2011): The Supply Chain Management Casebook: Comprehensive Coverage and Best Practices in SCM. FT Press Operations Management.<\/p>\n

          e) Drake (2015): Advances in Business, Operations, and Product Analytics: Cutting Edge Cases from Finance to Manufacturing to Healthcare. Pearson FT Press.<\/p>\n

          \n","protected":false},"author":4,"menu_order":9,"template":"","meta":{"pb_show_title":"on","pb_short_title":"","pb_subtitle":"","pb_authors":["dr-sudhanshu-joshi"],"pb_section_license":""},"chapter-type":[],"contributor":[58],"license":[],"class_list":["post-151","chapter","type-chapter","status-publish","hentry","contributor-dr-sudhanshu-joshi"],"part":3,"_links":{"self":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapters\/151","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapters"}],"about":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/wp\/v2\/types\/chapter"}],"author":[{"embeddable":true,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/wp\/v2\/users\/4"}],"version-history":[{"count":5,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapters\/151\/revisions"}],"predecessor-version":[{"id":161,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapters\/151\/revisions\/161"}],"part":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/parts\/3"}],"metadata":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapters\/151\/metadata\/"}],"wp:attachment":[{"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/wp\/v2\/media?parent=151"}],"wp:term":[{"taxonomy":"chapter-type","embeddable":true,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/pressbooks\/v2\/chapter-type?post=151"},{"taxonomy":"contributor","embeddable":true,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/wp\/v2\/contributor?post=151"},{"taxonomy":"license","embeddable":true,"href":"https:\/\/ebooks.inflibnet.ac.in\/mgmtp04\/wp-json\/wp\/v2\/license?post=151"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}