Procurement spend analysis with category classification and savings ID

A Quantisage Open Source Project — Enterprise-grade supply chain intelligence

• Overview
• Architecture
• Problem Statement
• Solution Deep Dive
• Quick Start
• Code Examples
• Academic Foundation
• Author

Procurement Spend Analyzer addresses a critical challenge in modern supply chain management. This implementation combines rigorous academic methodology with production-ready Python code designed for enterprise deployment.

Based on: Professor Robert Monczka, Arizona State

Procurement spend analysis with category classification and savings ID. In today's volatile supply chain environment — marked by geopolitical disruptions, climate risks, demand volatility, and rapid digitization — organizations need tools that go beyond traditional spreadsheet-based analysis.

• Production-ready Python implementation with clean, extensible architecture
• Academically grounded methodology from world-class research institutions
• Configurable parameters for enterprise-scale operations (1K to 100K+ SKUs)
• Comprehensive output metrics with sensitivity analysis and trade-off curves
• API-ready design for integration with ERP, WMS, TMS, and planning systems
• Fully transparent algorithms — no black boxes, every decision is explainable

flowchart LR A[📥 Input Data] --> B[⚙️ Processing] B --> C[🔢 Optimization] C --> D[📊 Results] D --> E[📋 Actions] style C fill:#fff9c4 style E fill:#c8e6c9 

graph LR A[Input] --> B[Analyze] B --> C[Optimize] C --> D[Execute] D --> E[Monitor] E -->|Feedback| B style C fill:#fff9c4 

Supply chain procurement is a persistent operational challenge with direct impact on cost, service, and resilience:

The complexity compounds when you consider:

• Scale: Thousands of SKUs × hundreds of locations × 365 days = millions of decisions per year
• Uncertainty: Demand volatility, supply disruptions, lead time variability, price fluctuations
• Dependencies: Upstream and downstream ripple effects across multi-tier networks
• Constraints: Capacity limits, budget constraints, regulatory requirements, sustainability targets

"Supply chains compete, not companies. The supply chain that can sense, plan, and respond fastest — wins."

This implementation follows a structured six-phase approach:

1. Data Ingestion & Validation — Load operational data, validate completeness, handle missing values, detect outliers
2. Exploratory Analysis — Statistical profiling, distribution analysis, correlation identification, pattern detection
3. Model Construction — Build the core analytical model with configurable parameters and business rule constraints
4. Solution Computation — Execute the algorithm with convergence monitoring and solution quality metrics
5. Sensitivity Analysis — Systematic parameter variation to understand solution robustness and critical drivers
6. Results & Deployment — Generate actionable outputs with clear recommendations and expected impact quantification

# Clone the repository git clone https://github.com/virbahu/procurement-spend-analyzer.git cd procurement-spend-analyzer # Create virtual environment (recommended) python -m venv .venv source .venv/bin/activate # Linux/Mac # .venv\Scripts\activate # Windows # Install dependencies pip install -r requirements.txt # Run python spend_analyzer.py

from procurement_spend_analyzer import * # Run with default parameters result = main() print(result)

# Customize for your environment # See source code docstrings for full parameter reference

numpy pandas 

Based on: Professor Robert Monczka, Arizona State

Virbahu Jain — Founder & CEO, Quantisage

Building the AI Operating System for Scope 3 emissions management and supply chain decarbonization.

MIT License — see LICENSE for details.

_{Part of the Quantisage Open Source Initiative | AI × Supply Chain × Climate}