-
Notifications
You must be signed in to change notification settings - Fork 0
encounter data
Syed Ibrahim Omer edited this page Apr 12, 2026
·
5 revisions
US Customs and Border Protection (CBP) Southwest Land Border encounter statistics, serving as the ground truth for illegal border crossings.
- Publisher: US Customs and Border Protection
- URL: cbp.gov
- Format: 8 CSV files covering FY2019 – FY2026 YTDC
- Coverage: Southwest border, monthly aggregates
- Baseline: ~50,000/month in 2018–2019
The Collection Module (src/collection/encounter.py) scrapes CSV download links from cbp.gov using async semaphore-controlled downloads with retry logic. Files land in data/raw/encounter/.
The Processing Module (src/processing/merge.py) consolidates 8 CSV files:
- Scan all CSVs in encounter directory
- Map columns: Fiscal Year → year, month abbreviation → month number
- Concatenate using Polars lazy frames for efficiency
- Output: unified encounter DataFrame with standardized schema
- Extreme volatility: May 2023 peak of 880,000 encounters = 18× the 2018–2019 baseline
- Dual-channel correlation: r = 0.438 with legal visa issuances, suggesting common push/pull factors drive both legal and illegal migration
- Fiscal year alignment: Data reported by federal fiscal year (Oct–Sep), requiring conversion to calendar year for alignment with other sources
Encounter data serves as a secondary target/validation variable:
- Used in Cross-Correlation Analysis to validate that Google Trends signals predict both channels
- Appears in EDA notebooks for dual-axis visa-vs-encounter visualizations
- Validates that the system captures both legal and illegal migration dynamics
- Visa Data — Primary ground truth (legal immigration)
- Data Collection — Broader ingestion architecture
- Cross-Correlation Analysis — Encounter-trends analysis
- Collection Module — Source code reference
- Project Overview — Goals, research questions, methodology, and team
- Glossary — Key terms used throughout this wiki
Raw inputs that feed the prediction system.
| Page | Description |
|---|---|
| Visa Data | US Department of State visa issuance statistics (108 monthly PDFs) |
| Encounter Data | CBP Southwest border encounter statistics (FY2019–2026) |
| Google News | 170K+ news articles across 15 countries × 8 topics |
| Google Trends | Monthly search-interest time series (15 countries × 8 keywords) |
| Exchange Rates | IMF Real Effective Exchange Rate for 6 countries |
The end-to-end flow from raw data to production forecasts.
| Page | Description |
|---|---|
| Data Collection | Ingestion layer: async scraping, bounded concurrency, retry logic |
| Data Processing | PDF parsing, JSON→Parquet, encounter merging |
| NLP Enrichment | Embedding → Clustering → Labeling → Sentiment |
| Panel Construction | Feature engineering: 18 lag features, 6 lead targets |
| Training Pipeline | Out-of-time train/test split, 4 architectures |
| Inference Pipeline | Horizon-aware ensemble, production prediction flow |
Machine learning architectures and their roles in the ensemble.
| Page | Description |
|---|---|
| Random Forest | cuML GPU Random Forest — best at short horizons (Lead 1–2) |
| LSTM | MigrationLSTM — country-aware with SurgeJointLoss |
| Transformer | MigrationTransformer — best at long horizons (Lead 5–6) |
| Horizon-Aware Ensemble | Dynamic weighting: RF→short, Transformer→long |
| SurgeJointLoss | Dual-objective loss: Huber + BCE for crisis detection |
| Jina v5 Embeddings | TensorRT INT8 news article embeddings (768-dim) |
| Flan-T5 Summarization | TensorRT INT8 cluster labeling engine |
Statistical techniques driving the lead-lag and surge analysis.
| Page | Description |
|---|---|
| Lead-Lag Analysis | Pearson correlation at 0–6 month offsets |
| Surge Detection | Quantile-based and σ-threshold spike identification |
| Sentiment Analysis | Rule-based lexicon scoring for migration-relevant news |
| Event Clustering | HDBSCAN GPU clustering + LED label generation |
| Cross-Correlation Analysis | CCF analysis, VAR benchmarking, ADF stationarity tests |
| Multiple Comparison Correction | Benjamini-Hochberg FDR for 58 significant signals |
What the system discovered about migration predictability.
| Page | Description |
|---|---|
| Event-Visa Findings | News events as leading indicators (r=0.617 at 3-month lag) |
| Exchange Rate Findings | Exchange rate signals (DR r=0.498 at 2-month lag) |
| Model Performance | Ensemble results: F1=0.96 at Lead 1, F1=0.86 at Lead 6 |
Reference documentation for every src/ subpackage and key files.
| Page | Description |
|---|---|
| Main Entry Point |
src/main.py CLI: bootstrap, collect-live, sync-data |
| Collection Module |
src/collection/* — visa, encounter, news, trends, HF sync |
| Processing Module |
src/processing/* — parse, merge, build_panel, summarize |
| Analysis Module |
src/analysis/* — events, exchange_rate, trends_analysis, plots |
| Models Module |
src/models/* — surge_model, train_and_evaluate, inference |
| News Scraper | Deep dive: batch decoding, checkpoint recovery, throttling |
| PDF Parser | Deep dive: PyMuPDF table extraction, VISA_MAP normalization |
| TensorRT Engines | Deep dive: Jina-v5, Flan-T5, LED TensorRT engines |
| Build Panel Detail | Deep dive: lag/lead construction, forward-fill strategies |
| HF Sync | Deep dive: bidirectional Hugging Face Hub sync |
Compute, reproducibility, and operational details.
| Page | Description |
|---|---|
| GPU Acceleration | TensorRT INT8, cuML, CUDA streams, NVML profiling |
| Reproducibility | HF bootstrap, run.sh pipeline, dependency checking |