supplyseer: Computational Supply Chain with Python
summary
A Python library called supplyseer provides runnable modules: a demand simulator using geometric Brownian motion to generate 1,000s of sample paths over a 365‑day horizon and report quantiles; a digital twin network that models 2 warehouses and 15 stores and compares three inventory policies (reorder‑point, diffusion‑inspired, hybrid), reports kinetic‑energy flow metrics and shows diffusion/hybrid eliminate stockouts while classical produces stockout spikes; a cooperative‑game analyzer with Shapley and Nash diagnostics; and a geopolitical risk tool that queries GDELT API to map conflicts to lead‑time (e.g., Ukraine ×5) and cost multipliers (e.g., cost ×7).
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:18Supply chain analytics challenges
- 8:45Installing supplyseer and demand simulation
- 10:14Demand simulation with stochastic processes
- 21:04Supply chain digital twin demo
- 43:29Game theory for power dynamics
- 1:03:08Geopolitical risk analysis
- 1:13:08Q&A
related talks
25mData Driven Supply Chain Network Design
33mUntangling the complexity of demand forecasting models: building a Market Simulator
40mDomain-driven Data Science
01h 23mA Hands-On Introduction to Your First Data Science Project
01h 00mAutomation: Amazon’s Supply Chain Optimization Technologies (SCOT)
26mRiddles in Supply Chain Management - How AI solves them?
30mBuild on-demand logistics apps with Python, OR-Tools, and DecisionOps
29mDecision sciences in Python