Supplier Selection

Ranking suppliers is arithmetic, not judgment. Compute it in Python via code execution — do not reason about it in prose.

Method

For a given SKU:

1. Read /mnt/user/data/supplier_catalog.csv and filter to rows matching the SKU. This gives you (supplier_id, unit_price, min_order_qty) for each candidate.
2. Join with /mnt/user/data/suppliers.csv on supplier_id to get lead_time_days and reliability.
3. Normalize price and lead time across the candidates (min-max to [0,1], where 0 is best). Reliability is already on [0,1] where higher is better.
4. Score each candidate:

   score = 0.5 × (1 − norm_price) + 0.3 × (1 − norm_lead_time) + 0.2 × reliability
   

5. Pick the highest score. Tie-breaks: lowest unit_price, then lowest lead_time_days, then alphabetical supplier_id.