IE 438

INVENTORY MANAGEMENT AND CONTROL

INVENTORY SIMULATION TOOL USER GUIDE

Kaan Akçınar
Mehmet Salih Çelik
İbrahim Yiğit Menekşe
Efe Erden
Muhammed Gaffar Ava
User Guide for the Inventory Simulation Tool

Introduction
The Inventory Simulation Tool is designed to help users simulate and analyze inventory levels based on
various parameters, demand distributions, inventory policies, lead times, and service level targets. This
tool is intended for inventory managers, supply chain professionals, and students to model inventory
dynamics and optimize stock management.

Key Terms and Concepts

Demand Distribution

Describes how demand varies over time. Different types of distributions (e.g., Normal, Poisson,
Uniform) model different demand scenarios.

● Normal Distribution: Represents demand fluctuating around an average with predictable

variability.
● Poisson Distribution: Models random, discrete events like order arrivals.
● Uniform Distribution: Assumes demand is evenly distributed within a range.

Inventory Policy

Determines how and when inventory is replenished.

● s,Q Policy: Restock a fixed quantity when inventory drops below a threshold.
● R,S Policy: Periodically review inventory and restock to a predefined maximum level.
● Continuous Review: Continuously monitor inventory and reorder as needed.

Lead Time

The time it takes for an order to arrive after placing it.

● Fixed Lead Time: Delivery time is constant and predictable.

● Stochastic Lead Time: Delivery time varies due to external factors.
Service Level

A measure of how effectively demand is met without stockouts.

● Cycle Service Level: The probability of no stockouts during a replenishment cycle.

● Fill Rate: The percentage of total demand fulfilled directly from inventory.

Getting Started
Installation

1. Python Environment: Ensure Python 3.7 or higher is installed in a python environment

such as PyCharm etc.
2. Required Libraries: Install the necessary libraries using the following command before
importing:
!pip install numpy pandas matplotlib openpyxl
3. Running the Tool: Execute the Python script to launch the tool.
inventory_simulation_tool.py
Launching the GUI

Once the tool is launched, the user interface (UI) will appear. Follow the sections below to
configure and run the simulation.

Figure 1. User Interface of the Inventory Simulation Tool

User Interface Breakdown
Demand Distribution

This option allows users to select the type of demand distribution for the simulation. The
available options are:

● Normal Distribution: Use when demand is consistent around an average value with
some variability.

Parameters: Mean (average demand), Standard Deviation (variability around the mean).

Figure 2. “Normal” Distribution Interface

● Poisson Distribution: Suitable for scenarios with random and discrete demand (e.g.,
order counts).

Parameter: Lambda (average demand per unit time).

Figure 3. “Poisson” Distribution Interface

● Uniform Distribution: Use for scenarios where demand is evenly distributed within a
range.

Parameters: Low (minimum demand), High (maximum demand).

Figure 4. “Uniform” Distribution Interface

When to Choose:

● Select "Normal" if you expect demand to fluctuate predictably around an average.

● Choose "Poisson" for sporadic, discrete orders.
● Use "Uniform" for unpredictable demand that varies equally within a known range.

Inventory Policy

Defines the replenishment strategy for inventory. Available options include:

● s,Q: Reorder a fixed quantity (Q) when inventory falls below a threshold (s).

Best for stable demand and fixed order sizes.

Figure 5. (s,Q) Policy Selection from Drop Menu

● R,S: Review inventory periodically (R) and restock to a maximum level (S).

Useful for periodic reviews, such as weekly restocking.

Figure 6. (R,S) Policy Selection from Drop Menu

● Continuous Review: Monitor inventory continuously and reorder when it reaches a

threshold.

Ideal for critical items requiring constant monitoring.

Figure 7. “Continuous Review” Selection from Drop Menu

Lead Time Type

Specifies how long it takes for an order to arrive:

● Fixed: Lead time is constant and predictable.

Enter direct lead time.

Figure 8. “Fixed” Lead Time Selection from Drop Menu

● Stochastic: Lead time varies based on random factors.

Enter mean lead time; variability is modeled internally.

Figure 9. “Stochastic” Lead Time Selection from Drop Menu

When to Choose:

● Use "Fixed" for reliable suppliers with consistent delivery.

● Choose "Stochastic" for suppliers with unpredictable delivery times.

Service Level

Defines the target for meeting demand:

● Cycle Service Level: Probability of not stocking out during a replenishment cycle.

Example: 0.95 (95% chance of meeting demand).

Figure 10. “Cycle Service Level” Selection from Drop Menu

 ● Fill Rate: Percentage of total demand that can be met directly from stock.

Example: 0.90 (90% of demand is fulfilled).

Figure 11. “Fill Rate” Selection from Drop Menu

When to Choose:

● Use "Cycle Service Level" for short-term performance metrics.

● Choose "Fill Rate" for long-term demand satisfaction goals.

Simulation Duration

Set the number of days to simulate inventory. Recommended durations:

● Short-term analysis: 30–60 days.

● Long-term analysis: 90–180 days or more.

Figure 12. Simulation Duration Input Box

Running a Simulation
Example Scenarios

Scenario 1: Stable Demand (Normal Distribution)

1. Select Normal Distribution.

2. Enter Mean: 50, Standard Deviation: 10.
3. Choose (s,Q) Policy.
4. Set Fixed Lead Time: 3 days.
5. Enter Cycle Service Level: 0.95.
6. Set simulation duration: 30 days.
7. Click "Run Simulation".

Figure 13. User Interface With “Scenario 1” Inputs

Scenario 2: Unpredictable Demand (Uniform Distribution)

1. Select Uniform Distribution.

2. Enter Low: 10, High: 50.
3. Choose (R,S) Policy.
4. Set Stochastic Lead Time: Mean 5 days.
5. Enter Fill Rate: 0.90.
6. Set simulation duration: 35 days.
7. Click "Run Simulation".

Figure 14. User Interface With “Scenario 2” Inputs

Outputs and Analysis
Graphical Outputs

● On-Hand Inventory (Blue): Shows the available inventory after daily demand is met.
● In-Transit Inventory (Orange): Indicates inventory en route based on stochastic lead
time.
● Shortage (Green): Displays unmet demand for days with stockouts.

Figure 15. An Example Output of a Normally Distributed Demand with (s,Q) Policy
Interpreting the Graphs

Scenario 1

Figure 16. Graph Output of “Scenario 1”

On-Hand Inventory (Blue Line):

● Inventory levels rise steadily after replenishments, fluctuating due to demand.

● No dips indicate demand is met effectively without stockouts.

In-Transit Inventory (Orange Line):

● The constant line shows a fixed amount of inventory en route, likely due to consistent
ordering and lead time.

Shortage (Green Line):

● A flat line at 0 confirms there were no unmet demands or shortages during the simulation.
Scenario 2

Figure 17. Graph Output of “Scenario 2”

On-Hand Inventory (Blue Line):

● The inventory fluctuates frequently, dropping significantly when demand exceeds

available stock.
● Frequent replenishments prevent prolonged shortages, but inventory levels stay low
between orders.

In-Transit Inventory (Orange Line):

● Sharp spikes indicate frequent ordering and consistent lead times, replenishing inventory
regularly.
● The pattern suggests reliance on smaller, frequent orders to meet demand.
Shortage (Green Line):

● Periodic small spikes indicate occasional unmet demand, though these are quickly
resolved by replenishments.
● Shortages are minimal, implying that the policy is moderately effective but could be
improved for higher service levels.

Excel Output

The tool generates a Excel file (inventory_simulation_report.xlsx) containing 7 columns on the

“Day-by-Day” sheet, such as:

1. Day: The day of the simulation, ranging from Day 1 to the end of the simulation period.
2. On-Hand Inventory: The amount of inventory available at the end of each day after
fulfilling daily demand.
3. In-Transit Inventory: Inventory that is currently being delivered (due to lead time).
4. Shortage: The amount of unmet demand on a given day (if on-hand inventory is
insufficient).
5. Holding Costs: Costs associated with holding the inventory, calculated as a function of
the on-hand inventory.
6. Backorder Costs: Costs incurred due to shortages (penalty per unit of unmet demand).
7. Ordering Costs: Fixed cost incurred when an order is placed.

On the “Summary” sheet, you can see:

1. Total Holding Cost: Represents the cost of storing inventory over the simulation period.
2. Total Backorder Costs: These costs arise from unmet demand, penalizing shortages.
3. Total Ordering Costs: Fixed costs associated with placing orders.
4. Total Costs: The sum of all costs incurred during the simulation, combining holding,
backorder, and ordering costs.
Example Excel Output of Scenario 1

Figure 18. Excel Sheet Output of “Scenario 1”

Key Observations

1. On-Hand Inventory (Column B):

○ The inventory levels decrease steadily until a replenishment order is received.
○ Inventory dips close to zero on certain days (e.g., Days 17, 24, 28), leading to
occasional shortages.
2. In-Transit Inventory (Column C):
○ A fixed value of 150 indicates consistent replenishment quantities in transit,
determined by the lead time and reorder policy.
3. Shortages (Column D):
○ Shortages occur on days like Day 17, 24, and 28. These are moments when
demand exceeds the on-hand inventory before replenishment arrives.
○ Example: On Day 24, there is a shortage of 7.65 units, leading to a backorder
cost.
4. Holding Costs (Column E):
○ Holding costs are proportional to the on-hand inventory and are higher when
inventory levels are above 50 (e.g., Days 1–10).
○ Low holding costs occur when on-hand inventory is depleted (e.g., Day 17).
5. Backorder Costs (Column F):
○ Costs arise on days with shortages (e.g., Day 24 has a backorder cost of $38.24).
○ No backorder costs are incurred on days without shortages.
6. Ordering Costs (Column G):
○ Fixed ordering costs of $20 are incurred whenever a replenishment order is
placed.
○ Orders occur consistently due to the policy.