electricsheepafrica/african-customs-clearance-times

---
license: cc-by-4.0
task_categories:
- tabular-classification
- tabular-regression
tags:
- trade
- customs
- logistics
- afcfta
- sub-saharan-africa
- synthetic
- supply-chain
pretty_name: African Customs Clearance Times
size_categories:
- 10K<n<100K
---

# African Customs Clearance Times

Synthetic dataset of customs clearance operations across 12 Sub-Saharan African countries, modelling three operational scenarios relevant to trade facilitation and the African Continental Free Trade Area (AfCFTA).

## Dataset Summary

| Field | Value |
|-------|-------|
| Records | 30,000 |
| Countries | 12 |
| Scenarios | 3 |
| Records per scenario | 10,000 |
| Temporal range | 2018–2025 |

## Scenarios

| Scenario | Description |
|----------|-------------|
| `baseline` | Current-state customs operations with existing inefficiencies |
| `digitized_single_window` | Simulated adoption of national single-window electronic trade systems |
| `border_closures` | Disruption from border closures, strikes, or pandemic-related restrictions |

## Countries

Kenya, Nigeria, South Africa, Ghana, Tanzania, Ethiopia, Rwanda, Senegal, Côte d'Ivoire, Mozambique, Uganda, Zambia

## Variables

| Variable | Type | Description |
|----------|------|-------------|
| `record_id` | int | Unique identifier |
| `scenario` | str | baseline, digitized_single_window, or border_closures |
| `country` | str | Country name |
| `border_post` | str | Border crossing or port name |
| `corridor` | str | Trade corridor (origin-destination) |
| `year` | int | Year of transaction (2018–2025) |
| `commodity_type` | str | Category of goods traded |
| `trade_type` | str | Import, Export, or Transit |
| `clearance_time_hours` | float | Total time from submission to release (hours) |
| `document_processing_hours` | float | Time spent on document review |
| `physical_inspection_hours` | float | Time spent on physical goods inspection |
| `documentation_count` | int | Number of required documents |
| `compliance_rate` | float | Proportion of shipments fully compliant (0–1) |
| `informal_payment_incidence` | float | Probability of informal facilitation payments (0–1) |
| `cost_per_container_usd` | float | Direct clearance cost per TEU in USD |
| `single_window_adoption_pct` | float | Share of transactions processed via single window (0–1) |
| `pre_arrival_processing_pct` | float | Share using pre-arrival clearance (0–1) |
| `clearance_status` | str | Cleared, Held, or Rejected |
| `inspection_rate` | float | Proportion of shipments physically inspected (0–1) |
| `facilitation_score` | float | Composite trade facilitation score (0–1) |

## Key Design Decisions

- **Kenya Mombasa–Nairobi corridor**: Baseline median clearance ~72–120 hours (3–5 days), reflecting known bottlenecks at East Africa's busiest port.
- **Rwanda single window**: Simulates sub-24-hour clearance for the majority of transactions, reflecting Rwanda's lead in single-window adoption in the region.
- **Nigeria baseline**: Highest clearance times, reflecting complex multi-agency processes at Lagos ports.
- **Efficiency ranking**: Countries are ranked by trade facilitation maturity; this ranking shapes all scenario outputs.

## Intended Uses

- Trade facilitation policy simulation
- AfCFTA readiness benchmarking
- Logistics and supply-chain optimization research
- Machine learning on tabular trade data
- Comparative analysis of customs modernization interventions

## Limitations

This is a **synthetic dataset**. It captures statistical patterns informed by real-world customs performance indicators (World Bank Doing Business trade across borders, WCO data) but does not represent actual individual transactions. Use for research, education, and policy modelling—not for operational decisions.

## How to Generate

```bash
pip install -r requirements.txt
python generate_dataset.py
python validate_dataset.py
```

## License

CC BY 4.0 — You are free to share and adapt this material for any purpose, including commercial, with appropriate attribution.