Why 90% of Candlestick Patterns Fail: Building an Institutional AI Confluence Scanner in Python

Description and use

yfinance‑ta‑patterns boosts algorithmic trading by adding multi‑factor confluence scoring and automated trade setups.

Problem

Algorithmic trading bots built on classic candlestick patterns often underperform because the patterns are treated as random noise in institutional markets.

Outcome

The framework enables zero‑compile installation, full 61‑pattern scanning, multi‑factor confluence scoring, automated trade setups, and LLM‑ready briefs, addressing the low win rates of traditional candlestick bots.

Workflow

• Install yfinance‑ta‑patterns via pip or uv
• Load multi‑asset data with MarketDataLoader
• Detect candlestick patterns with PatternAnalyzer
• Score patterns with AIPatternScorer using EMA, RVOL, RSI, ATR
• Filter for confluence_score ≥ 0.70
• Print high‑confluence setups with entry, SL, TP targets
• Export JSON or Markdown briefs for LLM agents

Evidence

Zero‑C Build Installation by Default: Includes a built‑in vectorized pure‑Python/NumPy engine for core candlestick patterns — install in seconds with pip or uv without needing C compilers or TA‑Lib binaries.

Source

Multi‑Factor AI Confluence Engine: Calculates a deterministic quantitative confluence score (0.0‑1.0) evaluating EMA trend alignment (20/50/200), zero‑lookahead Relative Volume (RVOL), canonical Wilder's RSI (14), and ATR volatility expansion.

Source