PRODUCTION AND OPERATIONS SYSTEMS

TASK CHAPTER 4

SUPPLY CHAIN MANAGEMENT

The demand for headphones for stereo devices and MP3 players
For trotters, it allowed Nina Industries to grow almost 50% last year.
the number of joggers continues to rise, so Nina hopes that the demand
it also increases, because, until now, no laws have been enacted
security measures that prevent joggers from using headphones. The demand for
last year's headphones were as follows:

Demand Demand
My Month
(units) (units)
January 4,200 July 5,300
February 4,300 August 4,900
March 4,000 September 5,400
April 4,400 October 5,700
May 5,000 November 6,300
June 4,700 December 6,000

With a least squares regression analysis, what would you estimate it to be?
the demand for each month of the upcoming year?

x y xy x2 y
1 4200 4200 1 3958.97
2 4300 8600 4 4151.28
3 4000 12000 9 4343.59
4 4400 17600 16 4535,90
5 5000 25000 25 4728.21
6 4700 28200 36 4920.51
7 5300 37100 49 5112.82
8 4900 39200 64 5305,13
9 5400 48600 81 5497.44
10 5700 57000 100 5689.74
11 6300 69300 121 5882.05
12 6000 72000 144 6074,36
78 60200 418800 650 18766.67

= +

∑ 78
̅= → ̅ → ̅ 6.5
12
60200
̅= → ̅= → ̅ 5016.667
12

∑ 2∑ −∑ × ( 650 ∗ 60200 )- 78( ∗ 418800 )

= 2 → = → = 3766,67
−( ) 2 ( 12 * 650-) 78( ) 2

∑ 2∑ −∑ × ( 12 ∗ 418800 )- 78( * 60200 )

= 2 2 → = → = 192,30
−( ) ( 12 * 650-) 78( ) 2

= + → = 3766.67 + 192.30(x)
 MES Forecast
13 6266.67
14 6458,97
15 6651,28
16 6843.59
17 7035.90
18 7228.21
19 7420.51
20 7612.82
21 7805.13
22 7997.44
23 8189.74
24 8382.05

The historical demand for the product is

Demand
January 12
February 11
March 15
April 12
May 16
June 15

a) With a weighted moving average and weights of 0.60, 0.30, and 0.10,
calculate the forecast for July.

Fjuliop = juniop * 0.6 + mayo * 0.3 + abril * 0.1

Fjuliom = 15 * 0.6 + 16 * 0.3 + 12 * 0.1

Fjuliop = 15 units

b) Using a simple moving average of three months, determine the forecast for July.

+ +
=
3
12 + 16 + 15
=
3

Fjuliop = 14.33 units

c) Through simple exponential smoothing with α = 0.2 and a forecast for

June 13, calculate the forecast for July. Make all the assumptions that
I want.
MES DEMAND 0.2
January 12
February 11
 March 15
April 12
May 16
June 15 13
July 13.4

d) With a simple linear regression analysis, calculate the regression equation of

the preceding data of the claim.

MES DEMAND X squared X*Y

1 12 1 12
2 11 4 22
3 15 9 45
4 12 16 48
5 16 25 80
6 15 36 90
21 81 91 297

= +

∑ 2∑ −∑ × ( 91 ∗ 81) - 21( ∗ 297 )

= 2 2 → = → = 10,8
−( ) ( )2
( 6 ∗ 91) - 21

∑ 2∑ −∑ × ( 6 ∗ 297) - 21( ∗ 81 )
= 2 2 → = → = 0,7714
−( ) ( 6 * 91-) 21( ) 2

= + → = 10.8 + 0.7714(x)

Forecast
20

15

10 DEMAND
y = 0.7714x + 10.8 Linear (DEMAND)
5 R² = 0.4844

0
0 2 4 6 8

e) Using the regression equation from section d), calculate the forecast for July.

Y = 10.8 + 0.7714(x)

= 10,8 + 0,7714( )

Y = 16,1998

Pronóstico julio =16 unidades

3) The following tables show actual unit sales from six months and a
initial forecast for January.
Real Forecasted
January 100 80
February 94
March 106
April 80
May 68
June 94

a) Calculate the forecasts for the remaining five months using smoothing
simple exponential with = 0.2.

Real Forecasted
January 100 80
February 94 84
March 106 86
April 80 90
May 68 88
June 94 84

b) Calculate the DAM of the forecasts.

Demand Error
month RSFE Projection
real Absolute
January 100 80 20 20
February 94 84 10 10
March 106 86 20 20
April 80 90 -10 10
May 68 88 -20 20
June 94 84 10 10

n
RSFE
i 1 20 10 20 10  20 10
MAD 15
n 6

In this problem, you will test the validity of your forecasting model.
Below are the forecasts from the model used and the actual demand.

Week Forecast Real

1 800 900
2 850 1,000
3 950 1,050
 4 950 900
5 1,000 900
6 975 1 100

With the method established in the text, calculate the DAM and the tracking signal.
Then decide if the forecasting model you used provides results.
reasonable

Week Forecast Real Of the Real Of the absolute sum of the real
1 800 900 -100 100 -100
2 850 1000 -150 150 -250
3 950 1050 -100 100 -350
4 950 900 50 50 -300
5 1000 900 100 100 -200
6 975 1100 -125 125 -325

n
RSFE
I 1
MAD
n
n
625
=104.17
6

-325
= -3.12
DMA 104.17

There is not enough evidence to reject the forecasting model, so its assumptions are accepted.
recommendations.

5) The historical demand for a product is as follows:

Demand
April 60
May 55
June 75
July 60
August 80
September 75

a) With a simple moving average of four months, calculate a forecast for

October.
+ + +
=
4
75 + 60 + 80 + 75
=
4

= 72,5

b) Using simple exponential smoothing with α = 0.2 and a forecast for

September = 65, calculate a forecast for October.
My Demand α=0.2
Abril 60
May 55
June 75
July 60
August 80
September 75 65
October 67

= ( t - 1 )+∝ ( t(- 1 - F(t

) - 1)

Ft = 65 + 0.2(75 - 65)

=67 units

c) Using simple linear regression, calculate the trend line of the data.
historical. On the X-axis, April = 1, May = 2, and so on,
while the Y-axis represents demand.

My Demand X squared x*y y squared

1 60 1 60 3600
2 55 4 110 3025
3 75 9 225 5625
4 60 16 240 3600
5 80 25 400 6400
6 75 36 450 5625
21 405 91 1485 27875

= +

∑ 2∑ −∑ × ( 91 ∗ 405) - 21( ∗ 1485 )

= 2 2 → = a = 54
−( ) ( 6 ∗ 91) -21( ) 2

∑ 2∑ −∑ × ( 6 ∗ 1485) - 21( ∗ 405 )

= 2 2 → = b = 3.86
−( ) ( )2
( 6 ∗ 91) - 21

= + → = 54 + 3.86(x)

Demand
85
80
75
70 y = 3.8571x + 54 Demand
65 R² = 0.4844
Linear (Demand)
60
55
50
0 2 4 6 8
d) Calculate a forecast for October.

= +

Y = 54 + 3.86(7)

= 81,02
Forecast October = 81 units

6) The following table shows the predicted demand for a product with its
particular forecasting method, along with actual demand.

Forecast Real
1,500 1 550
1,400 1,500
1,700 1 600
1,750 1 650
1 800 1,700

a) Calculate the tracking signal with the mean absolute deviation and the sum
continues with forecast errors.

n
|RSFE|
i 1
MAD
n
n
Of
n Forecast Real (At-Ft)
Absol
1 1500 1550 50 50
2 1400 1500 100 100
3 1700 1600 -100 100
4 1750 1650 -100 100
5 1800 1700 -100 100
SUMMATION 450
MAD 90

Of Ts=(At-
n Forecast Real (At-Ft)
Absol Md)/MAD
1 1500 1550 50 50 0.5556
2 1400 1500 100 100 1.1111
3 1700 1600 -100 100 1,1111
4 1750 1650 -100 100 1,1111
5 1800 1700 -100 100 1.1111
SUMMATION 450 5

-150
= -1.67
90

b) Comment on whether your forecasting method provides good predictions.

 It can be said that the forecasting method is acceptable since the sum of its errors.
the forecasts are not very high.

The local supermarket buys lettuce every day to ensure a

really fresh product. Every morning he takes the leftover lettuces from the
the previous day and sells them to an intermediary who resells them to farmers,
who use them as food for their animals. This week, the
supermarket can buy fresh lettuce at $4 per box. It sells them
lettuces at $10 per box and the intermediary selling the old lettuces is
willing to pay $1.50 per box. The background shows that the demand
The lettuce for tomorrow will be 250 boxes, with a standard deviation of 34.
boxes. How many boxes of lettuce should the supermarket buy tomorrow?

Data
Demanda=250 cajas
σ :standard deviation = 34 boxes

Q= cantidad a pedir
the standard deviations to obtain the exhaustion probability

= $10 − $4 = $6

C0 = $4 - $1.5 = $2.5

P <=Cu/(Co * Cu) = 6 * (2.5 * 6)0.7059

z = NORMSINV (0.7059)= 0.541446

Q = 250 + 0.541446(34) = 268.4 boxes

It should be bought 268 boxes of lettuce

8) The daily demand for a product is 100 units, with a standard deviation
standard of 25 units. The interval between reviews is 10 days and the time of
Delivery is in 7 days. At the time of review, there are 50 units in stock.
If you want a service probability of 98%, how many units should you have?
to order?

Datos D: demanda = 100

σ : desviación estándar = 25
Order cycle time = 10 days
L: tiempo de entrega = 6 días

σT + L= √T + Lσ 2 =

√ ((10 + 6) ( 25 ) 2 )= 100

z = N O R M S I N V ( P) = N O R M S I N V (0.98)

z = 2.05

q = d (T + L) + z σT+ L = 1

q = 100(10 + 6) + 2.05(100)- 50 = 1755 units

R = 1755 units should be ordered

 9) Using the information from the table, calculate the periods in which they should be made
the orders using the period balancing and components method (Part
period balancing) when the ratio of setup cost and maintenance cost
the inventory is 200.

Weeks 1 2 3 4 5 6 7 8 9 10
Demand 41 44 84 42 84 86 7 18 49 30

QUANTITY
FOR COST X PART COST X
REQUEST ORDER PERIOD MAINTENANCE
41 200 0 0
85 200 44*1=44 44
169 200 44+84*2=212 212
211 200 212+42*3=338 338
42 200 0 0
126 200 84*1=84 84
212 200 84+86*2=256 256
7 200 0 0
25 200 18*1=18 18
74 200 18+49*2=116 116
104 200 116*30*3=206 206

Orders must be placed in the following weeks

In week 1
In week 4
In week 7

A distributor is experiencing high demand for air conditioners.

the distributor has planned a six-month supply detailed in the
next table:

Months 1 2 3 4 5 6
Demand 1000 1200 500 200 800 1000
Order Cost 2000 2000 2000 2000 2000 2000
Cost
1 1 1 1 1 1
Maintenance

Use the Wagner-Whitin method to define the procurement policy of

air conditioners that allow optimizing the total handling costs of
inventory.

11) The demand for an item is 1000 units per year. Placing an order costs
$10 and the annual cost to maintain the items in inventory is $2 each year.
a) How many items should be ordered?

2DS 2000
=√ = √ = 100 pieces/order
2

100
= = = 10 votes/year
10
 = 100

b) Assume there is a discount of $100 on each order if the ordered volume

exceeds 500. Should you place orders of 500 or stick to the decision that
Did he/she take in a)?

1000 100
( 5) += ( ) = ( 5) + ( 2) = 200 dollars/year
2 100 2
Annual total cost on 500 = 520 dollars/year

200 dollars
= 2 descuento = 2100 (= )
ñ
520 - 200 = 320 dollars / year

Option A is the better decision

12) Taylor Industry has been using a fixed period inventory system.
which involved counting all the inventory assets every month. However, the
the rise in labor costs has led that company to consider other
alternatives to reduce the amount of work involved in warehouses
of the inventory, but without increasing its costs, such as those of shortages. This
It is a random sample of 20 items from Taylor.

Number of Number of
Uso Anual ($) Uso Anual ($)
Article Article
1 1500 11 13000
2 12000 12 600
3 1200 13 42000
4 50000 14 9900
5 9600 15 1200
6 750 16 10200
7 2000 17 4000
8 11000 18 61000
9 800 19 3500
10 15000 20 2900

¿Qué le recomendaría a Taylor para reducir el costo de mano de obra? (Ilustre

using an ABC Plan

Number of Percentage
piece Annual use Accumulated Percentage
P18 61000 24,096% 24,096%
P4 50000 19,751% 43,848%
P13 42000 16,591% 60,438%
P10 15000 5,925% 66,364%
P11 13000 5,135% 71,499%
P2 12000 4,740% 76,239%
P8 11000 4,345% 80,585%
P16 10200 4,029% 84,614%
P14 9900 3,911% 88.525%
P5 9600 3,792% 92.317%
P17 4000 1,580% 93,897%
P19 3500 1,383% 95,279%
P20 2900 1,146% 96.425%
P3 2200 0.869% 97,294%
P7 2000 0.790% 98.084%
P1 1500 0,593% 98.677%
P15 1200 0.474% 99.151%
P6 800 0.316% 99.467%
P9 750 0.296% 99.763%
P12 600 0.237% 100%

Article 15 is essential to proceed with the operations. How

Would you recommend it to be classified?

a) We must focus on trying to maintain inventories with the parts that

represent an income to the company and those like piece 18 that to us
represents 24% of our total cost, use it or inventory it in such a way that
let's keep only the ones we need to reduce our inventory costs.

b) It falls within the classification of A, since it represents a cost that

reaches the established percentages at level C (not that high). The
The instructions tell us that this piece is essential for the company.

13) PCQ, Inc. has identified three criteria it wants to use for selection.
among three possible suppliers. The criteria are performance, suitability, and
quality. Use the Analytic Hierarchy Process to determine the best
provider through the following matrices:

Accurate partner comparisons - Criteria of

evaluation

Performance Suitability Quality

Performance 1 1/3 1/5

Suitability 3 1 4

Quality 5 1/4 1

Accurate couple comparisons -

Evaluation criteria
Performance P1 P2 P3

P1 1 3 4

P2 1/3 1 3

P3 1/4 1/3 1

Suitability P1 P2 P3

P1 1 2 1/5

P2 1/2 1 ½

P3 5 2 1

Quality P1 P2 P3

P1 1 1/5 ¼

P2 5 1 2

P3 4 1/2 1