Paper II: Technical Subject

2. Industrial Engineering

2.2 Production Planning

And
Inventory Control

2021 December 31
 What is Forecasting?
 Process of predicting a future
event based on historical data
 Educated Guessing
 Underlying basis of
all business decisions
 Production
 Inventory
 Personnel
 Facilities
 Importance of Forecasting

 Departments throughout the organization depend

on forecasts to formulate and execute their plans.

 Finance needs forecasts to project cash flows and

capital requirements.

 Human resources need forecasts to anticipate

hiring needs.

 Production needs forecasts to plan production

levels, workforce, material requirements,
inventories, etc.
 Types of Forecasts by Time Horizon

Quantitativ
• Short-range forecast e
methods
– Usually < 3 months
• Job scheduling, worker assignments
Detailed
• Medium-range forecast use of
system
– 3 months to 3 years
• Sales/production planning

• Long-range forecast
– > 3 years
Design
• New product planning
of system
Qualitative
Methods
 Qualitative Forecasting Methods

Qualitative
Forecasting

Models
Executive Market Delphi
Judgement Research/ Method
Survey

Smoothing
 Quantitative Forecasting Methods

Quantitative
Forecasting

Time Series Regression

Models Models

2. Moving 3. Exponential
1. Naive
Average Smoothing
a) simple a) level
b) weighted b) trend
c) seasonality
 Time Series Models

• Try to predict the future based on past

data

– Assume that factors influencing the past will

continue to influence the future
– Identifies the pattern and historic data and
extrapolates this pattern for future prediction.
 Product Demand over Time
Demand for product or service

Year Year Year Year

1 2 3 4
 Time Series Models Components

Random
Variables Trend

Seasonality Cycle
 Time Series Models Components
• Trend
A general growth, decline or stationary pattern on the long term
frame. Eg. Population growth

• Seasonality
The seasonal variation on the data pattern. Eg. Higher sales in
festivals.

• Cycles
Cyclical wave like variation that occur over several years. Eg. Bull
and bear cycle in share market

• Random Variables
Irregular variations due to unusual circumstances. Eg. Increased
visitors in Chandragiri due to snowfall
 Product Demand over Time

Trend component
Seasonal peaks
Demand for product or service

Actual demand
Random line
variation
Year Year Year Year
1 2 3 4
 Naive Approach

 Demand in next period is the same as

demand in most recent period
 May sales = 48 → June forecast = 48

 Usually not good

 Simple Moving Average

• Assumes an average is a good estimator of

future behavior
• Weight on each period are equal

A t + A t -1 + A t -2 + ... + A t -n 1
Ft 1 =
n

Ft+1 = Forecast for the upcoming period, t+1

n = Number of periods to be averaged
At = Actual occurrence in period t
 Simple Moving Average
A t + A t -1 + A t -2 + ... + A t -n 1
Ft 1 =
n
You’re manager in Amazon’s electronics
department. You want to forecast iphone sales for
months 4-6 using a 3-period moving average.
Sales
Month (000)
1 4
2 6
3 5
4 ?
5 ?
6 ?
 A t + A t -1 + A t -2 + ... + A t -n 1
Ft 1 =
Simple Moving Average n

You’re manager in Amazon’s electronics

department. You want to forecast iphone sales for
months 4-6 using a 3-period moving average.
Sales Moving Average
Month (000) (n=3)
1 4 NA
2 6 NA
3 5 NA
4 ? (4+6+5)/3=5
5 ?
6 ?
 Simple Moving Average

What if ipone sales were actually 3 in

month 4
Sales Moving Average
Month (000) (n=3)
1 4 NA
2 6 NA
3 5 NA
4 3? 5
5 ?
6 ?
 Simple Moving Average

Forecast for Month 5?

Sales Moving Average

Month (000) (n=3)
1 4 NA
2 6 NA
3 5 NA
4 3 5
5 ? (6+5+3)/3=4.667
6 ?
 Simple Moving Average

Actual Demand for Month 5 =

7
Sales Moving Average
Month (000) (n=3)
1 4 NA
2 6 NA
3 5 NA
4 3 5
5 ?7 4.667
6 ?
 Simple Moving Average

Forecast for Month 6?

Sales Moving Average
Month (000) (n=3)
1 4 NA
2 6 NA
3 5 NA
4 3 5
5 7 4.667
6 ? (5+3+7)/3=5
 Weighted Moving Average

• Gives more emphasis to recent data

Ft 1 = w 1A t + w 2 A t -1 + w 3 A t -2 + ... + w n A t -n 1

• Weights
– decrease for older data
– sum of weights is always 1.
Simple moving
average models
weight all previous
periods equally
Weighted Moving Average: 3/6, 2/6, 1/6

Month Sales Weighted

(000) Moving
Average
1 4 NA
2 6 NA
3 5 NA
4 ? 31/6 = 5.167
5 ?
6 ?
Weighted Moving Average: 3/6, 2/6, 1/6

Month Sales Weighted

(000) Moving
Average
1 4 NA
2 6 NA
3 5 NA
4 3 31/6 = 5.167
5 7 25/6 = 4.167
6 32/6 = 5.333
F4=D1*1/6+D2*2/6+D3*3/6
 Exponential Smoothing

• Assumes the most recent observations have

the highest predictive value
– gives more weight to recent time periods

Ft+1 = Ft + (At - Ft)

et

Ft+1 = Forecast value for time t+1 Need initial

At = Actual value at time t forecast Ft
to start.
 = Smoothing constant
 Exponential Smoothing

Ft+1 = Ft + (At - Ft)

i Ai
Week Demand
1 820 Given the weekly demand
2 775 data what are the exponential
3 680 smoothing forecasts for
4 655 periods 2-10 using =0.10?
5 750
6 802 Assume F1=D1
7 798
8 689
9 775
10
 Exponential Smoothing

Ft+1 = Ft + (At - Ft)

i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 F2815.50
= F1+ (A793.00
1–F1) =820+(820–820)
4 655 801.95 725.20=820
5 750 787.26 683.08
6 802 783.53 723.23
7 798 785.38 770.49
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
 Exponential Smoothing

Ft+1 = Ft + (At - Ft)

i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
F3 = F2+ (A2–F2) =820+(775–820)
4 655 801.95 725.20
5 750 787.26 683.08=815.5
6 802 783.53 723.23
7 798 785.38 770.49
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
 Exponential Smoothing

Ft+1 = Ft + (At - Ft)

i Ai Fi
Week Demand  = 0.1 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
4 655 801.95 725.20
5 750 787.26 683.08
6 802 783.53 723.23This process
7 798 785.38 770.49 continues
8 689 786.64 787.00
through week 10
9 775 776.88 728.20
10 776.69 756.28
 Exponential Smoothing

Ft+1 = Ft + (At - Ft)

i Ai Fi
Week Demand  = 0.1  = 0.6
1 820 820.00 820.00
2 775 820.00 820.00
3 680 815.50 793.00
4 655 801.95 725.20
5 750 787.26 683.08 What if the
6 802 783.53 723.23  constant
7 798 785.38 770.49 equals 0.6
8 689 786.64 787.00
9 775 776.88 728.20
10 776.69 756.28
 Exponential Smoothing

• How to choose α
– depends on the emphasis you want to place
on the most recent data

• Increasing α makes forecast more

sensitive to recent data
Forecast Effects of Smoothing Constant 

Ft+1 = Ft +  (At - Ft)

or Ft+1 =  At + (1- ) At - 1 + (1- )2At - 2 + ...
w1 w2 w3

Weights
= Prior Period 2 periods ago 3 periods ago
 (1 - ) (1 - )2

= 0.10
10% 9% 8.1%
= 0.90 90% 9% 0.9%
 Measures of Forecast Error
A good forecast has a small error
 Error = Demand - Forecast
n

a. MAD = Mean Absolute Deviation A

t=1
t - Ft
MAD =
n

b. MSE = Mean Squared Error

n

 A t - Ft 
2

MSE = t =1
n

c. RMSE = Root Mean Squared Error RMSE = MSE

 Ideal values =0 (i.e., no forecasting error)

 Inventory
 An inventory is the stock of any idle item or resource in
a firm for future. Eg. Raw materials, components, tools,
equipments, semi finished goods, finished goods etc.
 “Inventory for any organization is a necessary evil”
 Operations managers must balance inventory
investment and customer service.
Two important questions…..
Just-in-time (JIT) inventory
 How much should the size management is the
procuring of materials
of the order be placed ? immediately as they are
required for use in
 When should the order production and doing away
with a large inventory
be placed ?
 Functions of Inventory
 To decouple the firm from fluctuations
/uncertainties in demands and supplies
 to provide a stock of goods that will provide
a selection for customers
 To take advantage of quantity discounts
 To hedge against inflation
 To allow flexibility in schedule
 To ensure optimum utilization of equipment
and labour.
 Types of Inventory
 Raw material
 Purchased but not processed
 Work-in-process
 Undergone some change but not completed
 A function of cycle time for a product
 Maintenance/repair/operating (MRO)
 Necessary to keep machinery and
processes productive
 Finished goods
 Completed product awaiting shipment
 The Material Flow Cycle

Cycle time

95% 5%

Input Wait for Wait to Move Wait in queue Setup Run Output
inspection be moved time for operator time time
 Inventory Costs
 Holding costs - the costs of holding or “carrying”
inventory over time. Inventory is a form of
investment and interest/ opportunity cost is
associated with it.

 Ordering costs - the costs of placing an order and

receiving goods. For most items, the ordering cost
is constant , regardless of its size.

 Setup costs - cost associated with adjusting

machine tools or machine in changing over an
assembly line to a new item. It is independent of
production size.
 Inventory Models
• Deterministic Model
• Probabilistic Model
 Deterministic Model

• This is considered under an assumption of

certainty.
• This model assumes that all the variables
of the inventory are known.
• Economic Order Quantity is the
deterministic Model
 Economic Order Quantity (EOQ)
Assumptions:
•The demand (D) is constant and uniform.
•The item cost per unit (C) does not vary with
order size.
•Lead time (L) is constant.
•Ordering or setup cost (S) is constant.
•No shortage of inventory.
•The cost of holding per unit (H) is linear function
of number of items
 Inventory Usage Over Time

Usage rate Average

Order inventory
quantity = Q
Inventory level

on hand
(maximum
inventory Q
level) 2

ROP

Minimum 0
inventory
Time
L
 Minimizing Costs
Objective is to minimize total costs
Curve for total
cost of holding
and setup

Minimum
total cost
Annual cost

Holding cost
curve

Setup (or order)

cost curve
Optimal order Order quantity
quantity (Q*)
 The EOQ Model
Q = Number of pieces per order
D = Annual demand in units for the inventory item
S = Setup or ordering cost for each order
H = Holding or carrying cost per unit per year

Annual setup or ordering cost = (Number of orders placed per year)

x (Setup or order cost per order)

Annual demand Setup or order

=
Number of units in each order cost per order

D
= (S)
Q
 The EOQ Model
Q = Number of pieces per order
Q* = Optimal number of pieces per order (EOQ)
D = Annual demand in units for the inventory item
S = Setup or ordering cost for each order
H = Holding or carrying cost per unit per year

Annual holding cost = (Average inventory level)

x (Holding cost per unit per year)

Order quantity
= (Holding cost per unit per year)
2

Q
= (H)
2
 The EOQ Model
Q* = Optimal number of pieces per order (EOQ)

Optimal order quantity is found when annual

setup cost equals annual holding cost

D Q
S = H
Q 2
Solving for Q*
2DS = Q2H
Q2 = 2DS/H
Q* = 2DS/H
 An EOQ Example
Determine optimal number of needles to order
D = 1,000 units
S = $10 per order
H = $.50 per unit per year

2DS
Q* =
H
2(1,000)(10)
Q* = = 40,000 = 200 units
0.50
 An EOQ Example
Determine optimal number of needles to order
D = 1,000 units Q* = 200 units
S = $10 per order
H = $.50 per unit per year

Expected Demand D
number of= N = =
orders Order quantity Q*
1,000
N= = 5 orders per year
200
 An EOQ Example
Determine optimal number of needles to order
D = 1,000 units Q* = 200 units
S = $10 per order N = 5 orders per year
H = $.50 per unit per year
Number of working
Expected days per year
time =T=
between N
orders 250
T= = 50 days between orders
5
 An EOQ Example
Determine optimal number of needles to order
D = 1,000 units Q* = 200 units
S = $10 per order N = 5 orders per year
H = $.50 per unit per year T = 50 days
Total annual cost = Setup cost + Holding cost
D Q
TC = S + H
Q 2
1,000 200
TC = ($10) + ($.50)
200 2
TC = (5)($10) + (100)($.50) = $50 + $50 = $100
 Reorder Points
 EOQ answers the “how much” question
 The reorder point (ROP) tells when to
order
Demand Lead time for a
ROP = per day new order in days

=dxL
D
d=
Number of working days in a year
 Reorder Point Curve
Q*
Inventory level (units)

Slope = units/day = d

ROP
(units)

Time (days)
Lead time = L
 Reorder Point Example
Demand = 8,000 iPods per year
250 working day year
Lead time for orders is 3 working days
D
d=
Number of working days in a year
= 8,000/250 = 32 units

ROP = d x L
= 32 units per day x 3 days = 96 units
 Quantity Discount Models
 Reduced prices are often available when
larger quantities are purchased
 Trade-off is between reduced product cost
and increased holding cost

Total cost = Setup cost + Holding cost + Product cost

D Q
TC = S+ H + PD
Q 2
 Quantity Discount Models
A typical quantity discount schedule

Discount Discount
Number Discount Quantity Discount (%) Price (P)
1 0 to 999 no discount $5.00
2 1,000 to 1,999 4 $4.80

3 2,000 and over 5 $4.75

Holding Cost (H)= 20% of product cost

Ordering or setup cost (S) = $49 per order
 Quantity Discount Models
Steps in analyzing a quantity discount
1. For each discount, calculate Q*
2. If Q* for a discount doesn’t qualify, choose
the smallest possible order size to get the
discount
3. Compute the total cost for each Q* or
adjusted value from Step 2
4. Select the Q* that gives the lowest total
cost
 Quantity Discount Example
Calculate Q* for every discount 2DS
Q* =
IP

2(5,000)(49)
Q1* = = 700 cars/order
(.2)(5.00)

2(5,000)(49)
Q2* = = 714 cars/order
(.2)(4.80)

2(5,000)(49)
Q3* = = 718 cars/order
(.2)(4.75)
 Quantity Discount Example
Calculate Q* for every discount 2DS
Q* =
IP

2(5,000)(49)
Q1* = = 700 cars/order
(.2)(5.00)

2(5,000)(49)
Q2* = = 714 cars/order
(.2)(4.80) 1,000 — adjusted
2(5,000)(49)
Q3* = = 718 cars/order
(.2)(4.75) 2,000 — adjusted
 Quantity Discount Example
Annual Annual Annual
Discount Unit Order Product Ordering Holding
Number Price Quantity Cost Cost Cost Total
1 $5.00 700 $25,000 $350 $350 $25,700

2 $4.80 1,000 $24,000 $245 $480 $24,725

3 $4.75 2,000 $23.750 $122.50 $950 $24,822.50

Table 12.3

Choose the price and quantity that

gives the lowest total cost
Buy 1,000 units at $4.80 per unit
 Quantity Discount Models
Total cost curve for discount 2
Total cost
curve for
discount 1
Total cost $

Total cost curve for discount 3

b
a Q* for discount 2 is below the allowable range at point a
and must be adjusted upward to 1,000 units at point b

1st price 2nd price

break break

0 1,000 2,000
Order quantity
 Probabilistic Models and Safety
Stock
 Used when demand is not constant or
certain
 Use safety stock to achieve a desired
service level and avoid stockouts

ROP = d x L + ss

Annual stockout costs = the sum of the units short x the

probability x the stockout cost/unit
x the number of orders per year
 Safety Stock Example
ROP = 50 units Stockout cost = $40 per frame
Orders per year = 6 Carrying cost = $5 per frame per year

Demand in Lead
Probability
time
30 .2
40 .2
ROP  50 .3
60 .2
70 .1
1.0
 Safety Stock Example
ROP = 50 units Stockout cost = $40 per frame
Orders per year = 6 Carrying cost = $5 per frame per year

Safety Additional Total

Stock Holding Cost Stockout Cost Cost

20 (20)($5) = $100 $0 $100

10 (10)($5) = $ 50 (10)(.1)($40)(6) = $240 $290

0 $ 0 (10)(.2)($40)(6) + (20)(.1)($40)(6) = $960 $960

A safety stock of 20 frames gives the lowest total cost

ROP = 50 + 20 = 70 frames
Probabilistic Demand

Probability of Risk of a stockout

no stockout (5% of area of
95% of the time normal curve)

Mean ROP = ? kits Quantity

demand
350
Safety
stock
0 z
Number of
standard deviations
 Probabilistic Demand
Use prescribed service levels to set safety
stock when the cost of stockouts cannot be
determined

ROP = demand during lead time + ZdLT

where Z =number of standard

deviations
dLT =standard deviation of
demand during lead time
 Probabilistic Example
Average demand =  = 350 kits
Standard deviation of demand during lead time = dLT = 10 kits
5% stockout policy (service level = 95%)

Using Appendix I, for an area under the

curve of 95%, the Z = 1.65

Safety stock = ZdLT = 1.65(10) = 16.5 kits

Reorder point =expected demand during lead
time + safety stock
=350 kits + 16.5 kits of safety
stock
=366.5 or 367 kits
Thank you !