Select Radar: Deal Radar Job Radar Stock Radar
Stock Radar — Experimental

Multi-factor confluence
on DAX stocks.

Rules-based signal detection across 40 DAX stocks. Momentum, volume anomalies, analyst revisions. LLM adds interpretation — not the signal itself.

Not a trading bot. A signal detector. Fires only when multiple independent factors align.

Open-source MIT License 40 DAX Stocks Experimental
ARCHITECTURE PRINCIPLE

Rules → Signals  ·  LLM → Insight  ·  User → Strategy

The signal engine uses deterministic quant rules. The LLM layer adds narrative interpretation. This ensures reproducibility, backtestability, and no hallucinations in the signal layer.

Quant layer first.
LLM interprets after.

Step 01

Feature Extraction

Yahoo Finance API scans 40 DAX stocks. Extracts: price change, volume spike, 52-week position, analyst revisions, earnings surprises.

Step 02

Signal Engine

Deterministic rules detect confluences. Fires only when 2+ independent factors align: e.g. Momentum + Volume Spike + Analyst Upgrade.

Step 03

LLM Insight

LLM interprets the signal: "Why is this happening? Is it structural or one-time?" Adds narrative context — but never generates the signal itself.

stock.yaml
sources:
  - yahoo_finance  # 40 DAX stocks

features:
  - price_change_5d
  - volume_spike
  - analyst_revision
  - earnings_surprise
  - 52w_position

signal_engine:
  min_confluence: 2  # fires at 2+ factors
  signals:
    - MOMENTUM_BREAKOUT
    - VOLUME_ANOMALY
    - ANALYST_UPGRADE
    - EARNINGS_BEAT

llm_insight:
  provider: groq
  model: llama-3.3-70b
  role: interpretation_only  # NOT signal generation

delivery:
  channel: telegram
  time: "07:20"

A signal, not a data point.

Instead of "SAP: Analyst target +50%", you receive a confluence signal with interpretation. Context, not noise.

Delivered via Telegram · 07:20 AM

40 DAX stocks scanned daily

THIS MORNING
40 stocks scanned
SIGNALS
2 detected
SOURCE
Yahoo Finance
telegram · stock-radar · today 07:20
📈 STOCK RADAR — 14.03.2026 DAX Signals: 2 | Confluence detected 1. SAP SE (SAP.DE) — Score: 84/100 MOMENTUM_BREAKOUT + ANALYST_UPGRADE Price: +4.2% (5d) | Volume: +180% avg Analyst upgrades: 3 in 7 days Insight: Institutional buying likely underway after earnings surprise. Structural, not one-time. Confidence: High 2. Siemens AG (SIE.DE) — Score: 71/100 VOLUME_ANOMALY + EARNINGS_BEAT Q1 EPS: +12% vs. consensus Volume spike: 2.4× 30-day average ─── 40 stocks scanned. 2 confluence signals.

Quant signals.
LLM interpretation.

Each signal is generated by deterministic rules — not by an LLM. The LLM only adds the "why" after the signal fires.

MOMENTUM_BREAKOUT

Momentum Breakout

Price breaks above a significant resistance level with above-average volume. Detected by comparing 5-day return against 52-week percentile position.

VOLUME_ANOMALY

Volume Anomaly

Trading volume significantly above 30-day average — often precedes institutional accumulation or distribution before public announcements.

ANALYST_UPGRADE

Analyst Upgrade

Multiple analyst upgrades within a short window. Weighted by recency and magnitude of target price revision. More powerful in confluence with other signals.

EARNINGS_BEAT

Earnings Beat

EPS or revenue significantly above consensus estimates. The signal fires when the beat exceeds a threshold — not for every minor outperformance.

Run the Stock Radar yourself.

For Developers

Clone. Configure. Run.

Yahoo Finance source included. Configure your DAX watchlist, set confluence thresholds, run on any server.

  • Yahoo Finance API · No key required
View on GitHub
Status

Experimental — but functional.

40/40 DAX stocks scan successfully. Signal detection working. LLM insight layer in development. Not financial advice.

  • Yahoo Finance ✓ · BaFin source in progress
bash
$ git clone https://github.com/yourusername/radar-agents
$ cd radar-agents

$ python3 cli/run.py --radar stock --dry-run

Scanning 40 DAX stocks... done.
2 confluence signals detected.

Not financial advice. Use at your own risk.

Questions? Ideas?
Let's talk.