02b Deterministic Inventory Models

download 02b Deterministic Inventory Models

of 51

Transcript of 02b Deterministic Inventory Models

  • 8/9/2019 02b Deterministic Inventory Models

    1/51

    Deterministic Inventory Models

    (PartII)

    1Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    2/51

    Outline

    2Sasadhar Bera, IIM Ranchi

    Inventory Models

    Continuous Review Single Item Models

    Basic EOQ model

    Economic production quantity model

    Quantity discount model

    Determining Safety Stock and Reorder Point

    For variable demand and constant lead time

    For variable demand and variable lead time

  • 8/9/2019 02b Deterministic Inventory Models

    3/51

    Outline (Contd.)

    3Sasadhar Bera, IIM Ranchi

    Impact of Service Level on Safety Stock

    Determining Order Quantity for Periodic Review Models

    For variable demand and constant lead time

    For variable demand and variable lead time

    Visual System

    Two-bin system

    One-bin system

  • 8/9/2019 02b Deterministic Inventory Models

    4/51

    Introduction

    4Sasadhar Bera, IIM Ranchi

    The objective of inventory management is to provide the

    required level of customer service and to reduce the sum of

    all costs involved. To achieve these objectives, two basic

    questions must be answered:

    How much should be ordered at one time?

    When should an ordered be placed?

    Management must establish decision rules to answer these

    question so that inventory management personnel know

    when to order and how much.

  • 8/9/2019 02b Deterministic Inventory Models

    5/51

    Inventory Models

    5Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    6/51

    Inventory Models

    6Sasadhar Bera, IIM Ranchi

    Inventory control problem is closely related to the demand

    pattern. Demand is the principle factor in the design of

    inventory model.

    i. Deterministic

    a) Static demand: constant over time

    b) Dynamic demand: Demand is known withcertainty but varies from one time period to

    other.

    ii. Probabilistic

    a) Stationary demand: Demand probability densityfunction remains unchanged over time.

    b) Non-stationary demand: Demand probability

    density function changes with time.

  • 8/9/2019 02b Deterministic Inventory Models

    7/51

    Inventory Models (Contd.)

    7Sasadhar Bera, IIM Ranchi

    Other classification of an inventory problem is

    i. Single item inventory: Handles only one item or SKU.

    ii. Multiple item inventory: When the inventories consists

    of many items. Such inventory problems may have

    different types of limitations such as finance, coststructure, space etc. As the number of restrictions

    increases, the inventory problem becomes more

    complicated.

  • 8/9/2019 02b Deterministic Inventory Models

    8/51

    Continuous Review Single Item Models

    Basic EOQ ModelProduction Quantity Model

    Quantity Discount Model

    8Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    9/51

    EOQ Model

    9Sasadhar Bera, IIM Ranchi

    Economic Order Quantity(EOQ) - The order size for which

    total inventory cost is minimum known as EOQ. Acalculation is made which considers demand rate, ordering

    cost, holding cost, lead time, and service level.

    The function of the EOQ model is to determine the optimal

    order size that minimizes total inventory cost. There are

    different variations of EOQ model, depending on the

    assumptions made about the inventory system. We will

    discuss two basic versions:

    i. Basic EOQ model

    ii. Production quantity model

  • 8/9/2019 02b Deterministic Inventory Models

    10/51

    Basic EOQ Model

    10Sasadhar Bera, IIM Ranchi

    The basic EOQ model determines optimal order size that

    minimizes the sum of carrying costs and ordering costs. The

    assumptions considered are:

    i. Demand is known with certainty and is constant over

    time

    ii. The lead time is also known with certainty and constant

    over time

    iii. No shortages are allowed

    iv. The order quantity is received all at once (i. e.instantaneous replenishment).

    v. Decisions for one item can be made independently of

    decisions for other items

  • 8/9/2019 02b Deterministic Inventory Models

    11/51

    Basic EOQ Model (Contd.)

    11Sasadhar Bera, IIM Ranchi

    Inventory Pattern in Basic EOQ model

  • 8/9/2019 02b Deterministic Inventory Models

    12/51

    Basic EOQ Model (Contd.)

    12Sasadhar Bera, IIM Ranchi

    To determine optimal order size two types of cost are

    considered viz. ordering cost and inventory carrying cost.

    These two costs react inversely to each other. As order size

    increases fewer orders are required, causing the ordering

    cost to decline, whereas the average amount of inventory

    on hand will increase, resulting in an increase in inventory

    carrying cost. Thus in effect, the optimal order quantityrepresents a compromise between these two inversely

    related costs.

    D = Annual demandC0= ordering cost per order

    Ch= Inventory carrying cost (or holding cost) per unit item

    Q = Economic order quantity

  • 8/9/2019 02b Deterministic Inventory Models

    13/51

    Basic EOQ Model (Contd.)

    13Sasadhar Bera, IIM Ranchi

    The figure below shows the inverse relationship between

    ordering cost and inventory carrying cost.

  • 8/9/2019 02b Deterministic Inventory Models

    14/51

    Basic EOQ Model (Contd.)

    14Sasadhar Bera, IIM Ranchi

    Inventory carrying cost increases linearly with order size Q,

    while annual ordering cost decreases exponentially with

    order-size Q.

    The optimal order quantity occurs at the point where the

    total cost is minimum, which coincide exactly with the point

    where the inventory carrying cost curve intersects the

    ordering cost curve. The optimal value of Q can be

    determined by differentiating the total cost curve with

    respect to Q.

    Annual ordering cost = C0 * (D/Q)

    Average inventory level = (0 + Q)/2 = Q/2

    Annual inventory holding cost or carrying cost = Ch* (Q/2)

    Total inventory cost (TC) = C0*(D/Q) + Ch*(Q/2)

  • 8/9/2019 02b Deterministic Inventory Models

    15/51

    Basic EOQ Model (Contd.)

    15Sasadhar Bera, IIM Ranchi

    To determine optimal order,

    = 0

    Optimal order size = Qopt

    =

    Optimal number of order per year = Nopt =

    Order cycle time =

    Q

    )TC(

    h

    0

    C

    DC2

    OptQ

    D

    OptNdaysworkingofNumber

  • 8/9/2019 02b Deterministic Inventory Models

    16/51

    Production Quantity Model

    16Sasadhar Bera, IIM Ranchi

    In production quantity model, the order quantity is received

    gradually over time and the inventory level is depleted atthe same time it is being replenished.

    This situation is commonly found when the inventory user is

    also producer, as in a manufacturing operation where parts

    are produced by other section to use in assembly operation.

    This situation is also can occur when orders are delivered

    continuously over time or when a retailer is also the

    producer.

  • 8/9/2019 02b Deterministic Inventory Models

    17/51

    Production Quantity Model (Contd.)

    17Sasadhar Bera, IIM Ranchi

    In order to determine the average inventory level, we

    define the following parameters:

    Q = order quantity per order

    p = daily rate at which the order is received over time, also

    known as the production rate

    d = the daily rate at which the inventory is depleted

    In this model, we are still assuming that no shortages occur.

    Hence demand rate cannot exceed production rate i. e.

    d p . If d = p, items are consumed as fast as they are

    produced, there is no order size.

  • 8/9/2019 02b Deterministic Inventory Models

    18/51

    Production Quantity Model (Contd.)

    18Sasadhar Bera, IIM Ranchi

    Inventory pattern of production quantity model

  • 8/9/2019 02b Deterministic Inventory Models

    19/51

    Production Quantity Model (Contd.)

    19Sasadhar Bera, IIM Ranchi

    D = Annual demand

    C0= Setup cost per production run (ordering cost)

    Ch= Inventory carrying cost (or holding cost) per unit item

    Q = Economic order quantity known as lot size

    Time required to finish receiving an order = t/ = Q/p

    The amount of inventory that will be depleted or used upduring this time period = t/d = (Q/p)d

    As a result, the maximum inventory on hand = Q - (Q/p)d

    = Q(1- d/p)

    Average inventory level = (Q/2) (1- d/p)

    Inventory carrying cost = Ch(Q/2) (1- d/p)

  • 8/9/2019 02b Deterministic Inventory Models

    20/51

    Production Quantity Model (Contd.)

    20Sasadhar Bera, IIM Ranchi

    To determine optimal order,

    = 0

    Optimum lot size = Qopt=

    Length of production run = (Qopt/p)

    Number of production runs = Nopt =

    Q

    )TC(

    )p

    d

    1(C

    DC2

    h

    0

    optQ

    D

  • 8/9/2019 02b Deterministic Inventory Models

    21/51

    Quantity Discount Model

    21Sasadhar Bera, IIM Ranchi

    When items are purchase, suppliers often give a discount in

    price over a certain volume or quantity. This is done

    because of larger orders reduce the suppliers ordering

    costs and cheaper transportation.

    Many manufacturing companies receive price discounts for

    ordering in high volume from supplier. Retail stores receive

    price discounts for ordering merchandise in large

    quantities.

    A quantity discount is a price discount on an item ifpredetermined numbers of units are ordered.

  • 8/9/2019 02b Deterministic Inventory Models

    22/51

    Quantity Discount Model (Contd.)

    22Sasadhar Bera, IIM Ranchi

    The basic EOQ model can be used to determine the optimal

    order size with quantity discounts. The purchase price of

    the item being ordered:

    D = Annual demand

    C0= ordering cost per order

    Ch= Inventory carrying cost (or holding cost) per unit itemQ = Economic order quantity

    P = per unit price of item

    Total cost (TC) =

    The basic assumptions considered are instantaneous

    replenishment, and no shortages.

    PD2

    QC

    Q

    DC

    h0

  • 8/9/2019 02b Deterministic Inventory Models

    23/51

    Quantity Discount Model (Contd.)

    23Sasadhar Bera, IIM Ranchi

    Total cost curve shows step function behaviour

  • 8/9/2019 02b Deterministic Inventory Models

    24/51

    Quantity Discount Model (Contd.)

    24Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    25/51

    Quantity Discount Model (Contd.)

    25Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    26/51

    Quantity Discount Model (Contd.)

    26Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    27/51

    27Sasadhar Bera, IIM Ranchi

    Determining Safety Stock and Reorder Point

  • 8/9/2019 02b Deterministic Inventory Models

    28/51

    Determining Safety Stock and Reorder Point

    28Sasadhar Bera, IIM Ranchi

    Safety stock and reorder point calculation depends on the

    following factors:

    i. Demand type: Fixed demand or probabilistic demand

    ii. Service level: Allowable % of stock out

    iii. Lead time: Constant lead time or variable lead time

    iv. Frequency of reorder: One prefers replenishment to

    take place on a continuous basis. Japanese companies

    have managed to get their replenishment from suppliers

    three to four times a day in trips involving multiple

    deliveries or pickups called milk runs.

  • 8/9/2019 02b Deterministic Inventory Models

    29/51

    Safety Stock

    29Sasadhar Bera, IIM Ranchi

    Inventory level with safety stock

    Safety stock: It is an additional inventory that is kept to take

    care of demand and supply uncertainty. Safety stock reduces

    chances of stockout situation.

    Reorder Point

    Safety Stock

    Inventory

    Time

    Lead time

    Cycle Stock

    Avg. inventory

  • 8/9/2019 02b Deterministic Inventory Models

    30/51

    Safety Stock (Contd.)

    30Sasadhar Bera, IIM Ranchi

    The average inventory for a period (considering safety stock) is

    equal to average of opening inventory and ending inventory.

    Opening inventory = order quantity (Q) + safety stock (SS)

    Ending inventory = safety stock (SS)

    Average inventory = Q/2 + SS

  • 8/9/2019 02b Deterministic Inventory Models

    31/51

    Reorder Point for Basic EOQ Model

    31Sasadhar Bera, IIM Ranchi

    In basic EOQ model we assumed that demand is constant i. e.

    rate of demand is same. We also consider that lead time is

    constant i. e. we get order quantity in exactly specified timeperiod.

    Reorder point: The level of inventory at which a new order is

    placed. Determining the reorder point depends on thedemand during the lead time and the safety stock required. If

    demand during the lead time is greater than expected, there

    will be a stockout unless sufficient safety stock is available.

    Let d = demand rate during lead time

    L = lead time

    Reorder point (R) = d*L

  • 8/9/2019 02b Deterministic Inventory Models

    32/51

    Capturing Uncertainty in Demand and Supply

    32Sasadhar Bera, IIM Ranchi

    Uncertainty is captured by one of the following measures:

    range, standard deviation, and coefficient of variation.

    Demand distribution is captured by two parameters: mean

    demand and standard deviation of demand. Standard

    deviation of demand is essentially captures uncertainty indemand.

    Similarly, supply uncertainty has two parameters, average

    lead time and standard deviation of lead time.

  • 8/9/2019 02b Deterministic Inventory Models

    33/51

    Reorder Point with Variable Demand

    33Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    34/51

    Reorder Point with Variable Demand (Contd.)

    34Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    35/51

    Reorder Point with Variable Demand (Contd.)

    35Sasadhar Bera, IIM Ranchi

    Demand distribution during lead time

  • 8/9/2019 02b Deterministic Inventory Models

    36/51

    Reorder Point with Variable Demand (Contd.)

    36Sasadhar Bera, IIM Ranchi

    The only time a stockout is possible is during the lead time.

    Safety stock is needed to cover only that period in which the

    demand during lead time is greater than the average.

    If z = 1, it provides service level 84% . It indicates (100 -84)=

    16% chance of stockout situations. Similarly, z = 1.65,

    provides 95% service level. z = 3, provides 99.83% service

    level.

    Excel function:

    For service factor z = 2, service level = NORMDIST(2, 0,1,1) =

    0.977 = 97.7%

    For 90% service level, service factor = z = NORMSINV(0.90) =

    1.28

    d i f i bl d d

  • 8/9/2019 02b Deterministic Inventory Models

    37/51

    Reorder Point for Variable Demand and

    Variable Lead Time

    37Sasadhar Bera, IIM Ranchi

    In practice both demand and lead time are variable. In suchsituation, first we have to determine demand distribution

    and lead time distribution in same unit. Second we consider

    demand and lead time are independent.

    To determine the reorder point we have to determine mean

    and standard deviation of demand during lead time, which

    is also a random variable. Therefore we have to use

    conditional distribution to find out standard deviation of

    demand.

    R d P i t f V i bl D d d

  • 8/9/2019 02b Deterministic Inventory Models

    38/51

    Reorder Point for Variable Demand and

    Variable Lead Time (Contd.)

    38Sasadhar Bera, IIM Ranchi

  • 8/9/2019 02b Deterministic Inventory Models

    39/51

    39Sasadhar Bera, IIM Ranchi

    Impact of Service Level on Safety Stock

    f i l f k

  • 8/9/2019 02b Deterministic Inventory Models

    40/51

    Impact of Service Level on Safety Stock

    40Sasadhar Bera, IIM Ranchi

    Safety stock level= service factor (z) * Standard deviation of

    demand during lead time

    If we improves service factor, amount of safety stock

    increases. Service factor determine service level. If service

    factor improves from 0 to 1, service level increases by 34%and further improve by 1 unit would improves service level

    by 14%. At some point improving service factor service level

    improves marginally. Thus relationship between safety stock

    level and service factor is non-linear.

    f S i l S f S k

  • 8/9/2019 02b Deterministic Inventory Models

    41/51

    Impact of Service Level on Safety Stock (Contd.)

    41Sasadhar Bera, IIM Ranchi

    For 90% service level, service factor = z = NORMSINV(0.90) =

    1.28

    I f S i L l S f S k

  • 8/9/2019 02b Deterministic Inventory Models

    42/51

    Impact of Service Level on Safety Stock (Contd.)

    42Sasadhar Bera, IIM Ranchi

    d f k

  • 8/9/2019 02b Deterministic Inventory Models

    43/51

    How to Reduce Safety Stock

    43Sasadhar Bera, IIM Ranchi

    Managerial decisions to reduce safety stock

    Reduction in demand uncertainty: Minimize the deviation

    between actual demand and forecast value by using better

    forecasting method or by making contracts with known

    customers to generate stable demand.

    Reduction in supply uncertainty: work with the suppliers to

    reduce lead time, reduce suppliers internal processing

    time, and faster mode of transport. Otherwise, select

    suppliers based on on-time delivery, flexibility, and quality.

  • 8/9/2019 02b Deterministic Inventory Models

    44/51

    44

    Sasadhar Bera, IIM Ranchi

    Determining Order Quantity in Periodic

    Review Model

    P i di R i S t

  • 8/9/2019 02b Deterministic Inventory Models

    45/51

    Periodic Review System

    45

    Sasadhar Bera, IIM Ranchi

    In a continuous review system, the inventory position is

    monitored continuously so that an order can be placedwhenever the reorder point is reached.

    With a periodic review system, the inventory is checked and

    reordering is done only at specified time interval. Forexample, inventory may be checked and orders placed on a

    weekly, biweekly, monthly, or some other time interval.

    When a firm or business handles multiple products, the

    shipping and receiving of orders are easily coordinated

    under periodic review system.

    P i di R i S t

  • 8/9/2019 02b Deterministic Inventory Models

    46/51

    Periodic Review System (Contd.)

    46

    Sasadhar Bera, IIM Ranchi

    Firms running their MRP (material requirement planning)

    system place order once in a week, essentially follow theperiodic review system. Similarly, if a retailer places an

    order at the time of a salesmansvisit, the periodic review

    system is being followed.

    While reviewing inventory position, we know that the next

    opportunity for ordering will come only after a time interval

    (P) and subsequently replenishment will take place after the

    lead time (L). In case of continuous review system

    vulnerable period is lead time. In case of periodic review

    system vulnerable period is review period plus lead time.

    Periodic Review System

  • 8/9/2019 02b Deterministic Inventory Models

    47/51

    Periodic Review System (Contd.)

    47

    Sasadhar Bera, IIM Ranchi

    Once the inventory in stock is determined after specified time

    interval, an order is placed for an amount that will bring back to a

    desired inventory level. Hence for periodic review system orderquantity (Q) is variable amount.

    Periodic Review: Order Quantity with Variable

  • 8/9/2019 02b Deterministic Inventory Models

    48/51

    Periodic Review: Order Quantity with Variable

    Demand

    48

    Sasadhar Bera, IIM Ranchi

    Periodic Review: Order Quantity with Variable

  • 8/9/2019 02b Deterministic Inventory Models

    49/51

    Periodic Review: Order Quantity with Variable

    Demand and Variable Lead Time

    49

    Sasadhar Bera, IIM Ranchi

    Visual System

  • 8/9/2019 02b Deterministic Inventory Models

    50/51

    Visual System

    50

    Sasadhar Bera, IIM Ranchi

    Bin 2 Bin 1

    When bin 1 is empty,use bin 2 as backup and

    place an order

    Pick parts

    as required

    Two-bin system

    (Q system)

    Visual System

  • 8/9/2019 02b Deterministic Inventory Models

    51/51

    Visual System (Contd.)

    51

    Single-bin system: When inventory drops to level of Red tag,

    place new order

    ROP