Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12...
Transcript of Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12...
![Page 1: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/1.jpg)
Single Period Inventory Models
Yossi SheffiMass Inst of TechCambridge, MA
![Page 2: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/2.jpg)
OutlineSingle period inventory decisionsCalculating the optimal order size
NumericallyUsing spreadsheetUsing simulation
AnalyticallyThe profit function
For specific distributionsLevel of ServiceExtensions:
Fixed costsRisksInitial inventoryElastic demand
![Page 3: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/3.jpg)
Single Period Ordering
Seasonal itemsPerishable goodsNews printFashion itemsSome high tech productsRisky investments
![Page 4: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/4.jpg)
Selling Magazines
Weekly demand:
90 48 87 78 58 71 102 87 66 79 97 75 8957 86 95 67 89 70 113 52 84 62 91 71 6699 73 92 66 67 89 87 64 70 54 67 88 6279 79 105 76 73 78 50 107 80 78 51 79 80
Total: 4023 magazinesAverage: 77.4 Mag/weekMin: 51; max: 113 Mag/week
![Page 5: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/5.jpg)
Detailed Histogram
0
1
2
3
4
40 45 50 55 60 65 70 75 80 85 90 95 100 105 110 115 120Demand (Mag/Wk)
Freq
uenc
y (W
ks/Y
r)
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
Cum
m F
req.
(Wks
/Yr)
Average=77.4 Mag/wk
![Page 6: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/6.jpg)
Histogram
0
2
4
6
8
10
12
14
16
40 50 60 70 80 90 100
110
120
130
More
Demand (Mag/week)
Freq
uenc
y (W
ks/Y
r)
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
Cum
mul
ativ
e Fr
eque
ncy
![Page 7: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/7.jpg)
The Ordering Decision (Spreadsheet)
Assume: each magazine sells for: $15Cost of each magazine: $8
Order: 20 30 40 50 60 70 80 90 100 110 120 130 140 150 160 d/wk Prob.
40 0.00 $140 $210 $280 $200 $120 $40 -$40 -$120 -$200 -$280 -$360 -$440 -$520 -$600 -$680 50 0.04 $140 $210 $280 $350 $270 $190 $110 $30 -$50 -$130 -$210 -$290 -$370 -$450 -$530 60 0.10 $140 $210 $280 $350 $420 $340 $260 $180 $100 $20 -$60 -$140 -$220 -$300 -$380 70 0.21 $140 $210 $280 $350 $420 $490 $410 $330 $250 $170 $90 $10 -$70 -$150 -$230 80 0.29 $140 $210 $280 $350 $420 $490 $560 $480 $400 $320 $240 $160 $80 $0 -$80 90 0.19 $140 $210 $280 $350 $420 $490 $560 $630 $550 $470 $390 $310 $230 $150 $70
100 0.10 $140 $210 $280 $350 $420 $490 $560 $630 $700 $620 $540 $460 $380 $300 $220 110 0.06 $140 $210 $280 $350 $420 $490 $560 $630 $700 $770 $690 $610 $530 $450 $370 120 0.02 $140 $210 $280 $350 $420 $490 $560 $630 $700 $770 $840 $760 $680 $600 $520 130 0.00 $140 $210 $280 $350 $420 $490 $560 $630 $700 $770 $840 $910 $830 $750 $670
Exp. Profit: $140 $210 $280 $350 $414 $464 $482 $457 $403 $334 $257 $177 $97 $17 -$63
Newsboy Framework – Panel 1: “basic Scenario”
![Page 8: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/8.jpg)
Expected Profits
-$100
$0
$100
$200
$300
$400
$500
$600
20 40 60 80 100 120 140 160Order Size
Prof
it
![Page 9: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/9.jpg)
Optimal Order (Analytical)
The optimal order is Q*At Q* the probability of selling one more magazine is the probability that demand is greater than Q*The expected profit from ordering the (Q*+1)st magazine is:
If demand is high and we sell it:(REV-COST) x Pr( Demand is higher than Q*)
If demand is low and we are stuck:(-COST) x Pr( Demand is lower or equal to Q*)
The optimum is where the total expected profit from ordering one more magazine is zero:
(REV-COST) x Pr( Demand > Q*) – COST x Pr( Demand ≤Q*) = 0
REV-COSTPr( Demand Q*) = REV
≤
![Page 10: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/10.jpg)
Optimal OrderThe “critical ratio”: REV-COST 15 8Pr( Demand Q*) = 0.47
15REV−
≤ = =
0
2
4
6
8
10
12
14
16
40 50 60 70 80 90 100
110
120
130
More
Demand (Mag/week)
Freq
uenc
y (W
ks/Y
r
0%10%20%30%40%50%
60%70%80%90%100%
Cum
mul
ativ
e Fr
eque
ncy
![Page 11: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/11.jpg)
0
2
4
6
8
10
12
14
16
40 50 60 70 80 90 100
110
120
130
More
Demand (Mag/week)
Freq
uenc
y (W
ks/Y
r
0%10%
20%30%
40%50%60%
70%80%
90%100%
Cum
mul
ativ
e Fr
eque
ncy
$0
$100
$200
$300
$400
$500
$600
20 40 60 80 100
120
140
160
Order SizePr
ofit
Salvage ValueSalvage value = $4/Mag. 15 8Critcal Ratio 0.64
15 4REV COSTREV SLV
− −= = =
− −
$87
![Page 12: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/12.jpg)
The Profit FunctionRevenue from sold itemsRevenue or costs associated with unsold items. These may include revenue from salvage or cost associated with disposal.Costs associated with not meeting customers’ demand. The lost sales cost can include lost of good will and actual penalties for low service.The cost of buying the merchandise in the first place.
![Page 13: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/13.jpg)
The Profit Function
0
[ ] ( ) ( ) Q
X Q x
E Sales Q f x dx x f x dx∞
= =
= +∫ ∫i i
0
[ ] ( ) ( ) [ ]Q
x
E Unsold Q x f x dx Q E Sales=
= − = −∫ i
[ ] ( ) ( ) [ ]X Q
E Lost Sales x Q f x dx E Salesµ∞
=
= − = −∫ i
[ ] [ ] [ ] [ ]E Profit R E Sales S E Unsold L E Lost Sales C Q= + − −i i i i
![Page 14: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/14.jpg)
The Profit Function – Simple Case
[ ] [ ]E Profit R E Sales C Q= −i i
[ ] 1 ( )d E Sales F QdQ
= −
[ *] R CF QR−
= and: 1* R CQ FR
− −⎡ ⎤= ⎢ ⎥⎣ ⎦
Optimal Order:
( )= − − =i[ ] 1 ( ) 0d E Profit F Q R CdQ
![Page 15: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/15.jpg)
Level of Service
Cycle Service – The probability that there will be a stock-out during a cycleCycle Service = F(Q)Fill Rate - The probability that a specific customer will encounter a stock-out
[ ][ ][ ]E SalesE Fill RateE Demand
=
![Page 16: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/16.jpg)
Level of Service
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
20 30 40 50 60 70 80 90 100 110 120 130 140 150 160
Order
Serv
ice
Leve
l
Cycle Service
Fill Rate
REV=$15COST=$7
![Page 17: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/17.jpg)
Normal Distribution of Demand
( )~ ,X N µ σ
( )[ ] ( ) ( )E sales Q z z zσ φ= − Φ +i i
σµ−
=Qz
[ ][ ] ( ) ( ) ( )Profit σ φ= − • − • ⋅ • Φ +E R C Q R z z z
-$200
-$100
$0
$100
$200
$300
$400
$500
20 40 60 80 100
120
140
160
Order Size
Expe
cted
Pro
fit
* R CQ NORMINVR−⎛ ⎞= =⎜ ⎟
⎝ ⎠
15 8 76 Mags15
NORMINV −⎛ ⎞= =⎜ ⎟⎝ ⎠
![Page 18: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/18.jpg)
Incorporating Fixed Costs
-$500
-$400-$300
-$200
-$100$0
$100$200
$300
$400$500
$600
20 30 40 50 60 70 80 90 100
110
120
130
140
150
160
Order SizeExpe
cted
Pro
fi
With fixed costs of $300/order:
REV=$15COST=$7
![Page 19: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/19.jpg)
Risk of Loss
0.00
0.20
0.40
0.60
0.80
1.00
20 40 60 80 100
120
140
160
Order Quantity
Prob
abili
ty o
f Los
s
REV=$15COST=$7
300/(15-7)=37.5. Below that there is no possibility to make money even if we sell ALL the order.
![Page 20: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/20.jpg)
Ordering with Initial InventoryGiven initial Inventory: Q0, how to order?
1. Calculate Q* as before2. If Q0 < Q*, order (Q*< Q0 )3. If Q0 ≥ Q*, order 0
With fixed costs, order only if the expected profits from ordering are more than the ordering costs
1. Set Qcr as the smallest Q such that E[Profits with Qcr]>E[Profits with Q*]-F
2. If Q0 < Qcr, order (Q*< Q0 )3. If Q0 ≥ Qcr, order 0
Note: the cost of Q0 is irrelevant
![Page 21: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/21.jpg)
-$100
$0
$100
$200
$300
$400
$500
$600
20 30 40 50 60 70 80 90 100 110 120 130 140 150 160
Initial Inventory
Expe
cted
Pro
fit
Ordering with FixedCosts and Initial Inventory
Example: F = $150
REV=$15COST=$7
•If initial inventory is LE 46, order up to 80•If initial inventory is GE 47, order nothing
![Page 22: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/22.jpg)
Elastic Demand
µ =D(P); σ = f(µ)Procedure:1. Set P2. Calculate µ3. Calculate σ4.
Expected Profit Function
$0
$100
$200
$300
$400
$500
$600
10 15 20 25 30Price
Prof
i t
− −⎛ ⎞= ⎜ ⎟⎝ ⎠
* 1 P CQ FP
5. Calculate optimal expected profits as a function of P.
Rev = $15Cost= $8µ(p)=165-5*pσ= µ/2
P* = $22Q*= 65 Magµ(p)=56 Magσ= 28Exp. Profit=$543
![Page 23: Single Period Inventory Modelsdspace.mit.edu/bitstream/handle/1721.1/39816/ESD-260...2 4 6 8 10 12 14 16 4 0 50 60 7 0 80 90 1 0 11 13 re Demand (Mag/week) Frequency (Wks/Yr 0% 10%](https://reader036.fdocuments.us/reader036/viewer/2022071216/60487d4ed98c11533418ad12/html5/thumbnails/23.jpg)
Any Questions?
Yossi Sheffi