Inventory Optimization and Scenario Simulation (El Niño)

Inventory Preparation

Forecasting Baseline

Visualization

Inventory Optimization and Scenario Simulation (El Niño)

This workflow analyzes inventory performance and simulates the impact of different business scenarios on stock levels, risk exposure, and profitability. It combines demand forecasting, stock calculations, and scenario-based parameter adjustments (price, cost, and lead time) to evaluate how changes affect inventory dynamics over time.

The process includes generating baseline forecasts, applying scenario shocks, and comparing results to highlight key impacts such as profit variation, stock duration, and inventory imbalance. This enables data-driven decision-making by providing clear insights into how extreme conditions influence operational performance and financial outcomes.

Data Reading

Panama Canal daily transits, 2023–24 (sourced and assumptions)

• Normal --> 36 daily transits

• Aug–Oct 2023 --> 32 (cap from 30th Jul 2023)

• Nov 2023 --> 25 (from 3rd Nov 2023)

• Dec 2023 --> 22. The level is sourced as the late-2023 low point; that it applied for all of December is assumed

• Jan 2024 --> 22. Assumed to continue, since the canal was back at about 31 only by mid-April 2024.

From these comes the capacity shortfall = 1 − transits / 36:

• 0.11 at 32 transits

• 0.31 at 25

• 0.39 at 22

Formulas

Month mapping: 2026 weeks 45–48 use November 2023, weeks 49–53 use December 2023, and 2027 weeks 1–4 use January 2024.

Changes added on top of the baseline:

• Lead time --> k_lt × shortfall in the same month

• Cost --> k_cost × shortfall two months earlier

• Price --> k_price × shortfall three months earlier

Each slider value / 100 is added to its matching change.

Assumptions

Exposure tiers. All 12 High-tier products come from supplier S3 and are among its higher-volume products. The 18 Medium-tier products come from S2 and S3. The remaining 30 products are Low tier.

Tier multipliers:

• High--> lead time: 2.0 // cost: 1.0 // price: 0.6

• Medium --> lead time: 1.0 // cost: 0.5 // price: 0.3

• Low --> lead time: 0.3 // cost: 0.15 // price: 0.1

Timing. Cost follows the canal shortfall two months later and price three months later. That reproduces the 2023–24 order: lead time first, then cost, then price. The exact lags are assumed.

Demand response:

• Price elasticity of −1.3.

• Forward buying: +0.5% demand per +1% lead time. This is the bullwhip effect, where customers order ahead when deliveries slow.

Deliveries. With the same volume in transit, a longer transit time means proportionally fewer units arrive each week. That’s Little’s law applied to the pipeline, as a modeling choice.

Scope:

• El Niño 2026 has the same intensity as 2023–24.

• Starting stock on 1 November is the same as the baseline.

• Sliders add the same change to all 13 weeks.

• Missed sales are lost, not carried forward to later weeks.