SOLUTION: CAL State LA Forecasting Demand Model & Cyclical Seasonal Patterns Questions


COLLIER/EVANS MindTap for Operations and Supply Association Management 9 Forecasting and Demand Planning Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. LEARNING OUTCOMES 1 Describe the consequence of prospect to the appraise chain 2 Explain basic concepts of prospect and span train 3 Explain how to devote sincere moving medium and exponential smoothing standards 4 Describe how to devote yield as a prospect approach 5 Explain the role of condemnation in prospect 6 Describe how statistical and condemnational prospect techniques are applied in practice Forecasting • Process of pendulous appraises of one or over variables into the forthcoming • Key element in: • Supply association administration systems • Customer connection administration systems • Revenue administration systems Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 3 Need for Forecasts in a Appraise Chain Forecast Planning Horizon • Planning horizon: Length of span on which a obviate is based • Spans from limited-range obviates of beneath 3 months to covet-range obviates of 1 to 10 years • Span bucket: Unit of appraise for the span period used in a obviate Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 5 Data Patterns in Span Series, Portio 1 • Span train: Set of observations appraised at successive points in span or aggravate successive periods of span • Characteristics - Trend: Underlying precedent of development or decline in a span train - Seasonal precedents: Characterized by repeatable periods of ups and downs aggravate limited periods of time Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 6 Data Patterns in Span Series, Portio 2 - Cyclical precedents: Regular precedents in a postulates train that seize assign aggravate covet periods of span - Unpremeditated departure (noise): Unexplained deviation of a span train from a predictable precedent - Irregular departure: One-span departure that is explainable Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 7 Example Straight and Nonstraight Trend Patterns Forecast Error, Portio 1 • Difference among the observed appraise of the span train and the obviate (At − Ft) • Mean Square Mistake (MSE) - Where T is all periods of postulates in the span series - At is real (observed) appraise - Ft is obviateed appraise Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 9 Forecast Error, Portio 2 • Mean Absolute Deviation mistake (MAD) - Where T is all periods of postulates in the span series • Mean Absolute Percentage Mistake (MAPE) Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 10 Statistical Forecasting • Based on the self-assertion that the forthcoming obtain be an extrapolation of the gone-by • Methods • Span train - Extrapolates unvarnished span-series data • Yield - Extrapolates unvarnished span-series postulates and other theoretically causal factors that influence the conduct of the span train Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 11 Simple Moving Average • Moving medium (MA) obviate: Medium of the most fresh “k” observations in a span train Ft+1 = ∑(most fresh “k” observations)/k = (At + At−1 + At−2 + … + At−k + 1)/k • As the appraise of k increases, the obviate reacts slowly to changes in the span train • As the appraise of k decreases, the obviate reacts quickly to changes in the span train • Effective for limited planning horizons where fawn-for is relatively steady and consistent Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 12 Simple Moving Medium - Examples K=3 F9 = (A8 + A7 + A6) / 3 F17 = ( A16 + A15 + A14) / 3 K=5 F9 = (A8 + A7 + A6 + A5 + A4) / 5 Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 13 Single Exponential Smoothing (SES), Portio 1 • Uses a weighted medium of gone-by span-series values to obviate the appraise of the span train in the contiguous period • Where - α - Smoothing perpetual (0 ≤ α ≤ 1) and is approximately similar to Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 14 Single Exponential Smoothing (SES), Portio 2 • Large appraises of α assign over reason on fresh data • Small appraises of α is preferred when a span train is volatile and contains stout unpremeditated variability • Disadvantages • Obviate obtain lag real appraises if a span train exhibits a overbearing trend • Obviate obtain aggravateshoot real appraises if the span train exhibits a indirect trend Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 15 Single Exponential Smoothing (SES) Example Ft+1 = Ft + α ( At – Ft) F10 = F9 + α ( A9 – F9 ) α = 0.1 to 0.9 Or α = Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 16 Regression Analysis, Portio 1 • Helps elevate a statistical standard that defines a connection among a hanging wavering and one or over inhanging waverings • Sincere yield - Appraise of a span train (the hanging wavering) is a employment of a single inhanging wavering, span (t) Yt = a + bt • Where - Yt - Estimate appraise in span t - a - Intercept of the unswerving line - b - Slope of the unswerving line Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 17 Excel’s Add Trendline Option • Helps ascertain the best-fitting yield standard for a span train • Straight and a multiformity of nonstraight employmental forms are available to fit the postulates • Displays R-squared appraises for the postulates entered - R-squared appraise is a appraise of departure in the hanging wavering due to the inhanging wavering (t) Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 18 Multiple Straight Yield Model • Works after a while over than one rebellious variable • Incorporates span and other causal variables Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 19 Judgmental Forecasting • Relies upon estimations and speedyise of nation in developing obviates • Approaches • Grassroots prospect: Asking those who are close to the end consumer environing the customers’ purchasing plans • Delphi arrangement - Prospect by speedy estimation by gathering judgments and estimations of key personnel based on their test and knowledge Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 20 Forecasting in Practice, Portio 1 • Managers use a multiformity of condemnational and quantitative prospect techniques • First stalk in developing a obviate involves understanding its purpose • Choosing a prospect arrangement depends on: • • • • • Time span for which a obviate is nature made Needed number of obviate updating Data requirements Level of exactness desired Quantitative skills Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 21 Forecasting in Practice, Portio 2 • Tracking illustrious - Provides a arrangement for monitoring a obviate by quantifying bias • Bias: Tendency of obviates to suitably be larger or smaller than the real appraises of the span train - Values among plus and minus 4 evidence an adequate prospect standard Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 22 Tracking illustrious Tracking Illustrious = ∑ ( At – Ft) x T / ∑│At – Ft│ Copyright ©2019 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly available website, in sound or in portio. CH9 23 KEY TERMS, Portio 1 • • • • • • • • Forecasting Planning horizon Time bucket Time train Trend Seasonal precedents Cyclical precedents Random departure (or din) • • • • • Irregular departure Forecast mistake Statistical prospect Moving medium (MA) obviate Single exponential smoothing (SES) • Yield decomposition • Multiple straight yield model KEY TERMS, Portio 2 • • • • Judgmental prospect Grassroots prospect Delphi arrangement Bias SUMMARY • Process of pendulous the appraises of one or over variables into the forthcoming is unconcealed as prospect • Statistical prospect and yield decomposition are methods used for prospect • Judgmental prospect relies upon estimations and expertise of nation in developing obviates MGMT 3060 - 80 Summer 2020 Homework – 5 Student Name: Date: Questions: 1. Suppose that you were thinking environing beginning a new restaurant. How would you go environing prospect fawn-for and sales? Answer 1: 2. If a supervisor asked you whether to use span train prospect standards or regression-based prospect standards, what would you ascertain him or her? Answer 2: MGMT 3060 - 80 Summer 2020 3. Provide some examples of span train that exhibit a. trends b. seasonal precedents c. cyclical precedents Answer 3: ...
Purchase acceptance to see full attachment