Professional Documents
Culture Documents
Mahasiswa dapat memahami konsep peramalan dan menggunakan teknik peramalan untuk menduga jumlah permintaan pada periode yang akan datang
Demand Management
Qualitative Techniques
technique,
Independent vs. dependent demand Market research, focus groups, Delphi 1. Time series based models 2. Associative (causal) Models
Quantitative Techniques
using MAD, MAPE, MSE, RMSE 2. Controlling Forecasting Process via Tracking Signal
Independent
demand items are the only items demand for which needs to be forecast These items include:
Finished goods and Spare parts
Independent Demand
(finished goods and spare parts)
Dependent Demand
(components)
B(4)
C(2)
D(2)
E(1)
D(3)
F(2)
Demand estimates for independent demand products and services are the starting point for all the other forecasts in POM. Management teams develop sales forecasts based in part on demand estimates. Sales forecasts become inputs to both business strategy and production resource forecasts.
Forecast Method(s)
Demand Estimates
Sales Forecast
Management Team
Business Strategy
Forecast Horizon
Long-Range
Time Span
Units of Measure
Dollars, tons, etc.
Years
MediumRange
Months
Short-Range
Weeks
Specific product quantities Machine capacities Planning Purchasing Scheduling Workforce levels Production levels Job assignments
Qualitative
Technique
Managers Opinion Executives Opinion Sales Force Composite Number of Firms
Low Sales
(less than $100M)
High Sales
(more than $500M)
Sumber : Nada Sanders and Karl Mandrodt (1994) Practitioners Continue to Rely on Judgmental Forecasting Methods Instead of Quantitative Methods, Interfaces, vol. 24, no. 2, pp. 92-100. Note: More than one response was permitted.
Biasanya berdasarkan pertimbangan faktor pemicu demand (products atau services) Tidak membutuhkan demand history, lebih pada produk/jasa baru Pendekatan bervariasi dari teknik surbey sampai intuisi masa depan
Executive committee consensus Delphi method Survey of sales force Survey of customers Historical analogy Market research
Berdasarkan pada asumsi bahwa forces masa lalu akan mempengaruhi demand masa depan : sejarah akan berulang Analysis pada pola demand masa lalu merupakan dasar untuk meramal deman masa depan Didominasi oleh analisis time series
Technique
Moving Average Simple Linear Regression
Low Sales
(less than $100M) 29.6% 14.8%
High Sales
(more than $500M) 29.2 14.6
Naive
Single Exponential Smoothing Multiple Regression Simulation Classical Decomposition Box-Jenkins Number of Firms
18.5%
14.8% 22.2% 3.7% 3.7% 3.7% 27
14.6
20.8 27.1 10.4 8.3 6.3 48
Sumber : Nada Sanders and Karl Mandrodt (1994) Practitioners Continue to Rely on Judgmental Forecasting Methods Instead of Quantitative Methods, Interfaces, vol. 24, no. 2, pp. 92-100. Note: More than one response was permitted.
A time series adalah sekumpulan angka yang diambil secara urut, contoh : demand masa lalu Analisis Time series identik dengan pola Sekali pola telah diidentifikasi, pola tersebut akan dipakai untuk melakukan peramalan
Sales
x x x
xx x x xx x x x x x x x x x x x x x x x xxxx
x x
x x x
x x
Year
Trends are noted by an upward or downward sloping line Seasonality is a data pattern that repeats itself over the period of one year or less Cycle is a data pattern that repeats itself... may take years Irregular variations are jumps in the level of the series due to extraordinary events Random fluctuation from random variation or unexplained causes
160
Power Demand
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 Year
Length of Season
4 12 52 4 28-31 7
Determining the use of the forecast--what are the objectives? Select the items to be forecast Determine the time horizon of the forecast Select the forecasting model(s) Collect the data Validate the forecasting model Make the forecast Implement the results
Linear Regression Simple Moving Average Weighted Moving Average Exponential Smoothing (exponentially weighted moving average) Exponential Smoothing with Trend (double smoothing)
Hubungan antara satu variabel independen X, and variabel dependent Y. Diasumsikan linear (a straight line) Form: Y = a + bX
Yt = a + bx
0 1 2 3 4 5 (weeks) x
b adalah slope.
a = y - bx
xy - n(y)(x) x - n(x )
2 2
b=
Week 1 2 3 4 5
Slide 26 of
y = 143.5 + 6.3t
180 175 170 165 160 155 150 145 140 135
1 2 3 4 5
Sales
Sales Forecast
Period
Slide 27 of
Accuracy adalah kriteria performansi pada pendekatan forecasting Accuracy adalah seberapa tepat nilai ramalan dibandingkan nilai aktual
Keakuratan forecasting perlu dimonitor untuk mengukur tingkat kepercayaan peramalan dan perubahan market yang memungkinkan peninjauan kembali terhadap pendekatan peramalannya Keakuratan bisa diukur dengan beberapa cara :
n
n
MAD
(A - F )
i i i 1
MSE = (Syx)2 Nilai Syx yang kecil berarti titik-titik data ramalan berada disekitar garis dan rentang errornya kecil. Error standard yang lebih kecil menghasilkan ramalan yang semakin akurat. MSE = 1.25(MAD) ketika error ramalan berdistribusi normal
Month 1 2 3 4 5
Month 1 2 3 4 5
A
MAD =
t=1
- Ft
40 = = 10 4
Periode rataan given atau dipilih Ramalan untuk periode berikutnya merupakan rataan aritmetik dari data aktual periode yang dihitung Dikatakan simple average sebab setiap periode yang digunakan untuk menghitung mempunyai bobot yang sama
. . . lanjut
Dikatakan moving sebab data demand yang baru akan dipakai sedang yang terlama diabaikan Dengan meningkatnya periode rataan, respon ramalan terhadap fluktuasi demand lebih kecil (low impulse response) dan sebaliknya
Week 1 2 3 4 5 6 7 8 9 10 11 12
Demand 650 678 720 785 859 920 850 758 892 920 789 844
Week 1 2 3 4 5 6 7 8 9 10 11 12
Demand 3-Week 6-Week 650 678 720 785 682.67 859 727.67 920 788.00 850 854.67 768.67 758 876.33 802.00 892 842.67 815.33 920 833.33 844.00 789 856.67 866.50 844 867.00 854.83
Slide 37 of 55
950 900 850 800 750 d n a 700 m e 650 D 600 550 500 1 2 3 4 5 6 7 Week 8 9 10 11 12
D e
Slide 38 of 55
WMA merupakan variasi simple moving average dimana weights yang digunakan untuk menghitung rata-rata pada SMA sama, sedang pada WMA tidak sama Bobot tergantung pada pengaruh moving average . . . lanjut
weights harus ditambahkan sampai 1.0 dan umumnya menurun seiring dengan umur data Distribution weights menentukan respon ramalan
Ft = w 1 A t -1 + w 2 A t - 2 + w 3 A t-3 + ...+ w n A t- n
Week 1 2 3 4 Demand 650 678 720
w
i=1
=1
Tentukan ramalan periode ke 4 dengan WMA 3-T Weights (adding up to 1.0): t-1: .5 t-2: .3 t-3: .2
Week 1 2 3 4
Forecast
693.4
F4 = .5(720)+.3(678)+.2(650)
Weights digunakan untuk menghitung ramalan (moving average) dengan distribusi exponential Ramalan merupakan jumlah dari forecast paling akhir dan proporsi error ramalan
. . . more
Smoothing constant, a, harus berada antara 0.0 and 1.0 Nilai a besar akan menghasilkan impulse response ramalan besar Nilai a kecil menghasilkan impulse response ramalan kecil
Week 1 2 3 4 5 6 7 8 9 10
Demand 820 775 680 655 750 802 798 689 775
Tentukan ramalan exponential smoothing untuk periods 2 sampai 10 dengan a=.10 dan a=.60.
Let F1=D1
Week 1 2 3 4 5 6 7 8 9 10
Demand 820 775 680 655 750 802 798 689 775
0.1 820.00 820.00 815.50 801.95 787.26 783.53 785.38 786.64 776.88 776.69
0.6 820.00 820.00 820.00 817.30 808.09 795.59 788.35 786.57 786.61 780.77
Slide 46 of 55
Cost Accuracy Data available Time span Nature of products and services Impulse response and noise dampening
Not involving a broad cross section of people Not recognizing that forecasting is integral to business planning Not recognizing that forecasts will always be wrong (think in terms of interval rather than point forecasts) Not forecasting the right things (forecast independent demand only) Not selecting an appropriate forecasting method (use MAD to evaluate goodness of fit) Not tracking the accuracy of the forecasting models
Tracking Signal
Tracking signal =
MAD
(A - F )
i i i 1
MAD
40
35
Sales
30
25 20
0 1 2 3 4 5 6 7 8 9 10 11 Period
Consumer Confidence Index Consumer Price Index Housing Starts Index of Leading Economic Indicators Personal Income and Consumption Producer Price Index Purchasing Managers Index Retail Sales
Bedworth, Integrated Production Control Systems, John Wiley & Son, 1987 Kholid Sheikh, MRP II, Mc Graw Hill,2002 Umble, M & Srikanth LM, Synchronous Manufacturing, Spectrum Publishing Co, Inc, 1996 Schenederjaans, Just In Time Management Teory of Constrain, Goldrat Elsayed, Analysis & Control Production Systems, PHI, 1994 Fogarty, P & IM, 1991 Narasimhan, PPIC, 1985