Cleopatra — Insider Copytrade POC

Monitors SEC EDGAR Form 4 filings in near real-time, detects insider buy clusters, sends Slack alerts, and optionally executes trades via Alpaca.

Architecture

EDGAR (Form 4 feed)
      │
      ▼
ingestion/edgar_poller.py   ← polls every 10 min, dedupes by accession
      │
      ▼
ingestion/form4_parser.py   ← parses XML, detects 10b5-1 plans
      │
      ▼
db/schema.sql + db/db.py    ← SQLite (WAL mode): filings + signals tables
      │
      ▼
signals/filter_engine.py    ← buy-only, exclude 10b5-1, min $50k, role-weighted scoring
signals/cluster_detector.py ← counts unique insiders per ticker in rolling 30-day window
      │
      ├──► alerts/slack_alert.py   ← POST to Slack webhook when score ≥ threshold
      └──► broker/alpaca_client.py ← paper/live order: 2% position size, 10% per-ticker cap

Setup

cp .env.example .env
# edit .env with your credentials
pip install -r requirements.txt

Environment variables (.env)

Variable	Required	Default	Description
SLACK_WEBHOOK_URL	optional	—	Incoming webhook URL for alerts
ALPACA_KEY	optional	—	Alpaca API key
ALPACA_SECRET	optional	—	Alpaca API secret
ALPACA_BASE_URL	optional	https://paper-api.alpaca.markets	Use paper or live endpoint
DB_PATH	optional	insider.db	SQLite database file path
DATA_DIR	optional	data/filings	Directory for cached raw XML filings

Usage

# Initialize DB and ingest current EDGAR feed (one shot)
python main.py fetch-once

# Run continuous polling loop (every 10 minutes)
python main.py run

# Backtest signals already in the DB against historical prices
python main.py backtest

Key configuration (config.py)

Parameter	Default	Description
EDGAR_POLL_INTERVAL	600 s	Polling cadence
MIN_TRANSACTION_VALUE	$50,000	Ignore buys below this
MIN_CLUSTER_SIZE	1	Minimum unique insiders before a signal fires
CLUSTER_WINDOW_DAYS	30	Rolling window for cluster counting
HOLDING_PERIOD_DAYS	90	Days held per position (backtest + close trigger)
POSITION_SIZE_PCT	2%	Fraction of portfolio per trade
MAX_POSITIONS	20	Hard position limit
SCORE_ALERT_THRESHOLD	5.0	Minimum score to trigger Slack alert

Scoring

score = role_weight × log(total_value) × (1 + 0.5 × (cluster_size − 1))

Role weights: CEO 3.0 · CFO/President 2.5 · COO 2.0 · Director 1.5 · VP 1.2 · 10% owner 1.0

Backtesting

The backtest loads signals from the SQLite DB and fetches OHLC data via yfinance on demand (no local price cache). Raw XML filings are cached in DATA_DIR (data/filings/) by accession number to avoid re-downloading.

Metrics reported: win rate, average return, average alpha vs SPY, Sharpe ratio.

Modules

Path	Purpose
config.py	All thresholds and env-var loading
ingestion/edgar_poller.py	EDGAR Atom feed polling and deduplication
ingestion/form4_parser.py	Form 4 XML → structured dict; 10b5-1 detection
db/schema.sql	SQLite schema (filings, signals)
db/db.py	DB access layer
signals/filter_engine.py	Filing → signal pipeline
signals/cluster_detector.py	Cluster detection from DB
alerts/slack_alert.py	Slack webhook alert
broker/alpaca_client.py	Alpaca order execution
backtest/backtest.py	Historical backtest runner
main.py	CLI entry point

Requirements

• Python 3.11+
• See requirements.txt: requests, lxml, yfinance, python-dotenv, alpaca-trade-api