Given a list of inventory items with their current stock levels and a list of incoming orders with quantities, write a Python function to determine the optimal reorder points for each item to minimize stockouts while considering lead times and demand variability. You can assume a simplified demand forecasting model is provided.

MECE Framework: 1. Deconstruct Input: Parse inventory, orders, lead times, and demand variability. 2. Define Reorder Point Components: Calculate safety stock (using demand variability and desired service level) and lead time demand. 3. Formulate Reorder Point: Reorder Point = (Average Daily Demand * Lead Time) + Safety Stock. 4. Iterative Optimization: Implement a simulation or optimization algorithm (e.g., genetic algorithm, linear programming) to adjust service levels or safety stock parameters to minimize stockouts under various demand scenarios. 5. Output: Present optimal reorder points per item, along with associated service levels and projected stockout risks. This ensures comprehensive coverage and actionable insights.

To determine optimal reorder points, I'd implement a Python function leveraging a multi-faceted approach. First, I'd calculate the average daily demand for each item using the provided forecasting model. Next, I'd determine the lead time demand by multiplying average daily demand by the item's lead time. Crucially, I'd then calculate safety stock for each item. This involves considering demand variability (standard deviation of demand) and a desired service level (e.g., 95% or 98%) to determine the appropriate Z-score. Safety Stock = Z-score * Standard Deviation of Demand * sqrt(Lead Time). Finally, the Reorder Point = Lead Time Demand + Safety Stock. The function would iterate through all inventory items, applying this formula. For optimization, I'd introduce a feedback loop or simulation to test different service levels, adjusting them to minimize stockouts within acceptable holding cost parameters. This ensures a robust, data-driven reorder strategy.