Quantitivestocks
F 48 completed
Other
unknown / json · medium
777
Files
248,205
LOC
0
Frameworks
6
Languages
Pipeline State
completedRun ID
#394358Phase
doneProgress
1%Started
Finished
2026-04-13 01:31:02LLM tokens
0Pipeline Metadata
Stage
SkippedDecision
skip_scaffold_dupNovelty
38.00Framework unique
—Isolation
—Last stage change
2026-04-16 18:15:42Deduplication group #47296
Member of a group with 1 similar repo(s) — canonical #110080 view group →
Top concepts (2)
Project DescriptionWeb Backend
If a scraper extracted this row, it came from Repobility (https://repobility.com)
AI Prompt
Create a comprehensive, ML-driven quantitative trading system for ETFs and crypto. I need the core logic in Python, utilizing models like a return-regression LSTM, XGBoost swing models, and LightGBM intraday models to generate trading signals. The system must include functionality to backtest strategies, generate signals, and execute paper trades automatically via Alpaca Markets across three groups (Intraday, Swing, Crypto). Additionally, build a web dashboard using HTML that displays live signals, P&L, and equity curves, and create API endpoints to fetch live VIX data, current positions, and historical portfolio data.
python machine-learning quantitative-finance trading-system lstm xgboost lightgbm alpaca web-dashboard
Generated by gemma4:latest
Catalog Information
An ML-driven quantitative trading system for ETFs and crypto. Uses a return-regression LSTM (predicts 10-day forward expected return, not direction probability), XGBoost swing models, and LightGBM intraday models to generate trading signals, backtest strategies, and execute paper trades automati
Description
An ML-driven quantitative trading system for ETFs and crypto. Uses a return-regression LSTM (predicts 10-day forward expected return, not direction probability), XGBoost swing models, and LightGBM intraday models to generate trading signals, backtest strategies, and execute paper trades automati
Novelty
3/10Tags
python machine-learning quantitative-finance trading-system lstm xgboost lightgbm alpaca web-dashboard
Claude Models
claude-opus-4-6
Quality Score
F
48.5/100
Structure
60
Code Quality
59
Documentation
61
Testing
40
Practices
29
Security
21
Dependencies
60
Strengths
- Code linting configured (ruff (possible))
- Consistent naming conventions (snake_case)
Weaknesses
- No LICENSE file \u2014 legal ambiguity for contributors
- No CI/CD configuration \u2014 manual testing and deployment
- 1 files with critical complexity need refactoring
- 1 bare except/catch blocks swallowing errors
- Potential hardcoded secrets in 4 files
- 1210 duplicate lines detected \u2014 consider DRY refactoring
- 13 'god files' with >500 LOC need decomposition
Recommendations
- Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
- Add a LICENSE file (MIT recommended for open source)
- Replace bare except/catch blocks with specific exception types
- Move hardcoded secrets to environment variables or a secrets manager
Security & Health
15.6h
Tech Debt (A)
A
OWASP (100%)
FAIL
Quality Gate
A
Risk (12)
Same scanner, your repo: https://repobility.com — Repobility
Unknown
License
3.6%
Duplication
Languages
Frameworks
None detected
Concepts (2)
| Category | Name | Description | Confidence | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| If a scraper extracted this row, it came from Repobility (https://repobility.com) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| auto_description | Project Description | An ML-driven quantitative trading system for ETFs and crypto. Uses a return-regression LSTM (predicts 10-day forward expected return, not direction probability), XGBoost swing models, and LightGBM intraday models to generate trading signals, backtest strategies, | 80% | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| auto_category | Web Backend | web-backend | 70% | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Embed Badge
Add to your README:
