-
Notifications
You must be signed in to change notification settings - Fork 0
cross correlation
CCF (Cross-Correlation Function) analysis and VAR (Vector Autoregression) benchmarking for evaluating Google Trends as a migration predictor.
Before correlation analysis, all time series are tested for stationarity using the Augmented Dickey-Fuller (ADF) test. Non-stationary series are differenced until stationary.
For each (country, keyword, target) combination:
- Compute the correlation between the trends keyword and migration target at multiple lag offsets
- Identify the lag with maximum absolute correlation
- Test significance against a white-noise null hypothesis
Vector Autoregression models are fitted to evaluate whether Google Trends adds predictive power beyond autoregressive baselines:
- Baseline: AR model using only lagged visa/encounter values
- Test: VAR model adding Google Trends keywords
- Metric: RMSE improvement over baseline
| Finding | Value |
|---|---|
| Keywords showing significance | 55% |
| Mean RMSE improvement (out-of-sample) | −5.97% (slightly worse) |
| Best keywords |
us_asylum, cbp_one (for encounter prediction) |
| Worst keywords | Generic terms like us_immigration
|
Conclusion: Google Trends has limited standalone predictive power but contributes as a complementary signal in the multi-modal ensemble.
The analysis focuses on high-volume countries:
- Mexico, Guatemala, Honduras, El Salvador (Northern Triangle)
- Venezuela, Cuba, Colombia
- Auto-detected from news data via
load_focus_countries()
data/processed/production_outputs/
├── trends_corr_summary.parquet
├── trends_country_best_keywords.parquet
├── trends_panel_diagnostics.parquet
├── trends_var_benchmark.parquet
├── trends_analysis_report.md
└── trends_findings_report.md
30 plots in data/plots/trends_vs_migration/:
- Country-specific CCF plots
- Composite tracking plots (trends overlaid with encounters/visas)
src/analysis/trends_analysis.py — key functions:
-
load_focus_countries()— Auto-detect analysis countries -
parse_trend_file()— Handle"<1"encoding -
load_trends_long()— Wide-to-long unpivot -
load_visa_monthly()— Aggregate visa by country/month
- Google Trends — Source data
- Lead-Lag Analysis — Complementary Pearson correlation approach
- Multiple Comparison Correction — Statistical correction
- Analysis Module — Full source code reference
- Project Overview — RQ3 context
- 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 |