Business operating management

Yuzhi Zhao

chapter9.pptx

Home >Business & Finance homework help >Operations Management homework help >Business operating management

Forecasting and Demand Planning

COLLIER/EVANS

Operations + Supply Chain Management

LEARNING OUTCOMES, Part 1

Describe the importance of forecasting to the value chain

Explain basic concepts of forecasting and time series

Explain how to apply simple moving average and exponential smoothing models

OM6 | CH7

LEARNING OUTCOMES, Part 2

Describe how to apply regression as a forecasting approach

Explain the role of judgment in forecasting

Describe how statistical and judgmental forecasting techniques are applied in practice

OM6 | CH7

Forecasting

Process of projecting values of one or more variables into the future

Key component in:

Supply chain management systems

Customer relationship management systems

Revenue management systems

OM6 | CH9

Exhibit 9.1

Need for Forecasts in a Value Chain

LO 9.1

OM6 | CH1

Demand Planning Modules

LO 9-1

Integrate marketing, inventory, sales, operations planning, and financial data

OM6 | CH9

Forecast Planning Horizon

LO 9-2

Planning horizon: Length of time on which a forecast is based

Spans from short-range forecasts of under 3 months to long-range forecasts of 1 to 10 years

Time bucket: Unit of measure for the time period used in a forecast

OM6 | CH9

Data Patterns in Time Series, Part 1

LO 9-2

Time series: Set of observations measured at successive points in time or over successive periods of time

Characteristics

Trend: Underlying pattern of growth or decline in a time series

Seasonal patterns: Characterized by repeatable periods of ups and downs over short periods of time

OM6 | CH9

Data Patterns in Time Series, Part 2

LO 9-2

Cyclical patterns: Regular patterns in a data series that take place over long periods of time

Random variation (noise): Unexplained deviation of a time series from a predictable pattern

Irregular variation: One-time variation that is explainable

OM6 | CH9

Exhibit 9.2

Example Linear and Nonlinear Trend Patterns

LO 9-2

OM6 | CH1

Forecast Error, Part 1

LO 9-2

Difference between the observed value of the time series and the forecast (At − Ft)

Mean square error (MSE)

Where T is all periods of data in the time series

OM6 | CH9

Forecast Error, Part 2

LO 9-2

Mean absolute deviation error (MAD)

Where T is all periods of data in the time series

Mean absolute percentage error (MAPE)

OM6 | CH9

Statistical Forecasting

LO 9-3

Based on the assumption that the future will be an extrapolation of the past

Methods

Time series - Extrapolates historical time-series data

Regression - Extrapolates historical time-series data and other potentially causal factors that influence the behavior of the time series

OM6 | CH9

Simple Moving Average

LO 9-3

Moving average (MA) forecast: Average of the most recent “k” observations in a time series

As the value of k increases, the forecast reacts slowly to changes in the time series

As the value of k decreases, the forecast reacts quickly to changes in the time series

Effective for short planning horizons where demand is relatively stable and consistent

OM6 | CH9

Single Exponential Smoothing (SES), Part 1

LO 9-3

Uses a weighted average of past time-series values to forecast the value of the time series in the next period

Where

α - Smoothing constant (0 ≤ α ≤ 1) and is approximately equal to

OM6 | CH9

Single Exponential Smoothing (SES), Part 2

LO 9-3

Large values of α place more emphasis on recent data

Small values of α is preferred when a time series is volatile and contains substantial random variability

Disadvantages

Forecast will lag actual values if a time series exhibits a positive trend

Forecast will overshoot actual values if the time series exhibits a negative trend

OM6 | CH9

Regression Analysis, Part 1

LO 9-4

Helps build a statistical model that defines a relationship between a dependent variable and one or more independent variables

Simple regression - Value of a time series (the dependent variable) is a function of a single independent variable, time (t)

Where

Yt - Estimate of the energy cost in year t

OM6 | CH9

Regression Analysis, Part 2

LO 9-4

a - Intercept of the straight line that best fits the time series

b - Slope of the straight line that best fits the time series

Simple linear regression - Helps find the best values of a and b using the method of least squares

OM6 | CH9

Excel’s Add Trendline Option

LO 9-4

Helps find the best-fitting regression model for a time series

Linear and a variety of nonlinear functional forms are available to fit the data

Displays R-squared values for the data entered

R-squared value is a measure of variation in the dependent variable due to the independent variable (t)

OM6 | CH9

Multiple Linear Regression Model

LO 9-4

Works with more than one independent variable

Incorporates time and other causal variables

OM6 | CH9

Judgmental Forecasting

LO 9-5

Relies upon opinions and expertise of people in developing forecasts

Approaches

Grassroots forecasting: Asking those who are close to the end consumer about the customers’ purchasing plans

Delphi method

Forecasting by expert opinion by gathering judgments and opinions of key personnel based on their experience and knowledge

OM6 | CH9

Forecasting in Practice, Part 1

LO 9-6

Managers use a variety of judgmental and quantitative forecasting techniques

First step in developing a forecast involves understanding its purpose

Choosing a forecasting method depends on:

Time span for which a forecast is being made

Needed frequency of forecast updating

Data requirements

Level of accuracy desired

Quantitative skills

OM6 | CH9

Forecasting in Practice, Part 2

LO 9-6

Tracking signal - Provides a method for monitoring a forecast by quantifying bias

Bias: Tendency of forecasts to consistently be larger or smaller than the actual values of the time series

Values between plus and minus 4 indicate an adequate forecasting model

OM6 | CH9

KEY TERMS, Part 1

Forecasting

Planning horizon

Time bucket

Time series

Trend

Seasonal patterns

Cyclical patterns

Random variation (or noise)

Irregular variation

Forecast error

Statistical forecasting

Moving average (MA) forecast

Single exponential smoothing (SES)

Regression analysis

Multiple linear regression model

OM6 | CH7

KEY TERMS, Part 2

Judgmental forecasting

Grassroots forecasting

Delphi method

Bias

OM6 | CH7

SUMMARY

Process of projecting the values of one or more variables into the future is known as forecasting

Statistical forecasting and regression analysis are methods used for forecasting

Judgmental forecasting relies upon opinions and expertise of people in developing forecasts

OM6 | CH7

4LTR Press

OM6 | CH7