Dataset Overview
| Dataset Name | Supply Chain Management Dataset |
| Total Data Volume | 720,000+ business records (multi-year supply chain data for enterprises covering 1,200+ nodes) |
| Type of supply chain | Manufacturing supply chain / retail supply chain / cold chain logistics / cross-border supply chain / electrician compliance |
| Industry Coverage | Electronic manufacturing / auto parts / fast-forwards / medical circulation / garment textiles / food beverages |
| Core indicators | Purchase orders, stock levels, logistics time limits, supplier performance, demand projections, cost analysis, six dimensions, 500+ indicator |
| Time Span | Data on the particle size of 2018 - 2025 |
| Data Source | Enterprise ERP, WMS Warehousing Management System, TMS Transport Management System, SSP, Customs clearance data |
Detailed Description of Data Dimensions
| Field Name | Data Type | Value Range / Description |
|---|---|---|
| supply_chain_id | String(18) | De-sensitive supply chain identifier ID |
| node_type | Enum | SUPPLIER | MANUFACTURER | DISTRIBUTOR | RETAILER | WAREHOUSE | LOGISTICS |
| industry_sector | Enum | ELECTRONICS | AUTO_PARTS | FMCG | PHARMA | TEXTILE | FOOD_BEV |
| period_date | Date | Data recording dates 2018-01-01 to 2025-12-31 |
| granularity | Enum | DAILY | WEEKLY | MONTHLY |
| po_quantity | Integer | Number of purchase orders |
| po_fulfillment_rate | Float | Order performance rate 0.0 - 1.0 |
| inventory_level | Integer | Stock (SKU units) |
| inventory_turnover | Float | Inventory turnover rate (single/year) |
| safety_stock_days | Float | Number of days of secure inventory |
| lead_time_days | Integer | Pre-procurement time (days) |
| delivery_lead_time | Float | Logistics delivery time limits (hours) |
| otif_rate | Float | Adequate and punctual delivery rate (OTIF) 0.0 - 1.0 |
| transport_cost | Float | Single transport cost ($) |
| supplier_score | Float | Supplier ' s composite score 0.0 - 100.0 |
| quality_defect_rate | Float | Quality deficiency rate (PPM) |
| forecast_demand | Integer | Demand projection (SKU units) |
| actual_demand | Integer | Actual requirements (SKU units) |
| forecast_accuracy | Float | Forecast accuracy rate 0.0 - 1.0 |
| supply_chain_risk | Enum | LOW | MODERATE | HIGH | CRITICAL |
De-identified JSON Data Sample
AI Application Scenarios
Demand forecasting and replenishment optimization
Training in time series forecasting models (LSTM/Transformer) based on historical sales data, seasonal factors, promotional activities, etc., optimize safe stock setting and automatic replenishment strategies.
Smart planning of logistics paths
Multi-target path planning using enhanced learning (RL) and operational optimization algorithms combined with real-time transport, weather and transport data to reduce transport costs and increase OTF delivery.
Vendor risk assessment
Integrate multi-source data such as supplier performance data, external profiles, financial indicators, build risk transfer models for suppliers of GNN, and achieve early warning of supply chain disruptions.
Storage network optimization
The selection of storage sites and the allocation of stocks are optimized using mixed integer planning (MILP) and genetic algorithms, based on characteristics such as distribution of orders, distribution radius, storage cost, etc.
Supply chain cost analysis
The analysis of attribution costs for the supply chain components using the XGBoost/random forest model, identifying cost anomalies, and supporting the development of efficiency reduction programmes.
Questions and answers on the supply chain model
Based on RAG (Retrieval Enhancement Generation) technology, supply chain operating data are embedded in vector databases, and the supply chain area LLM smart question and answer system is structured to support management decisions.
Get This Dataset
Provide API access, offline delivery, customised sampling, etc.