Your first inventory simulation
Run your first inventory Monte Carlo simulation for a SKU and learn to read its results.
By the end of this tutorial you will have launched a simulation, identified the key metrics and understood the two main charts the system generates.
What you will need
- Access to the Inventory (Optimization) module in AInventory.
- At least one SKU with lead time and demand data configured.
- Holding cost and shortage cost values configured for the SKU (check with your administrator if they are not available).
The system generates thousands of random demand and lead time scenarios based on the SKU's historical distribution. With those scenarios it estimates the fill rate, costs and expected inventory levels for a given k factor. This allows you to compare alternatives without risking real stock.
Step 1 — Open the Inventory module
- In the sidebar, click Inventory (or Optimization, depending on your company's configuration).
- You will see the list of SKUs with their current parameters.
TODO: screenshot of the Inventory module main view
Step 2 — Select a SKU
- Locate the SKU you want to analyze. You can use the search bar or category filters.
- Click the SKU to open its detail panel.
- Confirm the panel shows the SKU parameters: lead time, average demand, standard deviation, holding cost, shortage cost.
TODO: screenshot of a SKU detail panel before launching the simulation
Step 3 — Launch the simulation
- In the SKU panel, click the Simulate (or Run simulation) button.
- The system runs the Monte Carlo simulation. Duration depends on the configured number of iterations; it typically takes 2–10 seconds.
- When finished, the results appear below the button.
TODO: screenshot of the "Simulate" button and loading state
Step 4 — Read the simulator metrics
After the simulation you will see a panel with the following metrics:
| Metric | What it measures |
|---|---|
| Fill Rate | Percentage of demand satisfied from available stock. E.g.: 95 % means 1 out of every 20 requested units will not be available. |
| Safety Stock | Extra units the system recommends keeping to absorb demand and lead time variability. |
| Target Stock | Inventory level to replenish to. Includes safety stock plus expected demand during lead time. |
| Holding Cost | Financial cost of keeping inventory (cost of capital × price × average stock). |
| Shortage Cost | Estimated cost of unfulfilled units (lost sales, penalties, etc.). |
| Total Cost | Sum of Holding + Shortage. This is the number to minimize. |
| Average Inventory | Average stock level over the simulation horizon. |
Increasing fill rate requires more stock → more holding cost. Reducing it lowers holding but raises shortage cost. The goal is to find the optimal balance — which is exactly what the next tutorial covers.
Step 5 — Read the charts
The simulation generates two charts:
Total cost vs k factor curve
The X axis is the k factor (multiple of the standard deviation of demand during lead time). The Y axis is the total cost (holding + shortage). The curve is U- or J-shaped:
- On the left (low k): shortage dominates because safety stock is insufficient.
- On the right (high k): holding dominates because safety stock is excessive.
- The minimum of the curve is the optimal point.
TODO: screenshot of the cost vs k curve with the minimum marked
Sawtooth chart
Shows the simulated evolution of inventory over time: it rises when an order arrives and falls as demand consumes it. The sawtooth pattern is normal and expected.
- If inventory reaches zero frequently → there is stockout risk; consider increasing k.
- If inventory never comes close to zero → you may be over-stocked; consider reducing k.
TODO: screenshot of the sawtooth chart
Result
You launched your first Monte Carlo simulation, read the inventory metrics and understood the two main charts. You have a full picture of how a SKU performs under the current k factor.
Next step: learn to find the k factor that minimizes total cost in Find the optimal k factor.