detect-fed-unamortized-discount-pattern

Compare weekly WUDSHO data against historical crisis windows using correlation, DTW, and shape features.

3|1|Updated Jan 12, 2026

Search Tags:#cross-validation #WUDSHO #shape-matching #DTW #FRED #financial-stress #baseline-windows

Ready to run

npx skills add https://github.com/fatfingererr/macro-skills --skill detect-fed-unamortized-discount-pattern

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: detect-fed-unamortized-discount-pattern
Source: https://github.com/fatfingererr/macro-skills/tree/main/skills/detect-fed-unamortized-discount-pattern
Command: npx skills add https://github.com/fatfingererr/macro-skills --skill detect-fed-unamortized-discount-pattern

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, requests, scipy, matplotlib, fastdtw, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Analysts often interpret WUDSHO movements as risk signals without quantifying their similarity to historical crisis patterns. This Skill provides a formal, shape-based comparison against established crisis windows and cross-validates with multiple stress indicators to reduce false positives.

Core Features & Use Cases

Shape-based pattern matching using correlation, DTW, and shape feature similarity.
Cross-validation with credit spreads, VIX, yield curve, and Fed balance sheet to confirm true stress signals.
Historical baseline windows (COVID_2020, GFC_2008, TAPER_2013, RATE_HIKE_2022) for contextual analysis.
Output: a structured JSON report with best match, stress details, composite risk score, and interpretation.

Quick Start

Run the quick analysis with the default settings to compare the latest WUDSHO window against the COVID_2020 baseline and generate a JSON report.

Command: python scripts/pattern_detector.py --quick
Output: output/pattern_analysis_YYYY-MM-DD.json

Frequently Asked Questions about detect-fed-unamortized-discount-pattern

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect financial stress patterns in weekly WUDSHO series using shape matching?▼

Detect financial stress patterns in WUDSHO series by computing correlation, dynamic time warping (DTW), and shape feature similarity against historical crisis windows like COVID_2020, GFC_2008, TAPER_2013, and RATE_HIKE_2022.

What is the best way to cross-validate Fed balance sheet movements with credit spreads and VIX?▼

Cross-validate Fed balance sheet movements by comparing WUDSHO shape similarity against crisis baselines while checking cross-indicator signals from credit spreads, VIX, yield curve, and Fed balance to reduce false positives.

Does this pattern detection approach work with pandas and scipy for time series analysis?▼

Yes, this pattern detection approach works with pandas and scipy, using numpy for numerical operations, requests for FRED data retrieval, fastdtw for dynamic time warping, and matplotlib for visualization.

What limitations should I expect when using dynamic time warping for baseline window comparison?▼

When using dynamic time warping for baseline window comparison, limitations include potential false positives from single-indicator analysis, which is why cross-validation with credit spreads, VIX, yield curve, and Fed balance sheet is required.

How do I generate a structured JSON report with a composite risk score for WUDSHO analysis?▼

Generate a structured JSON report with a composite risk score by running the pattern detection script, which outputs pattern_similarity_score, stress_confirmation, best match details, and interpretation to an output directory.