Skip to content
MelQuantLabPublic

About

Quantitative finance research in Python: bias-aware backtests, credit and cross-asset analysis, portfolio risk and reproducible investment workflows

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

MelQuantLab

Analyze. Model. Alpha.

MelQuantLab is my growing portfolio of quantitative research, financial-data analysis and systematic-investing projects. The repository is deliberately organised as a learning and research journey: foundational programming first, then market-data analysis, followed by deeper investment research.

Research philosophy

Observe → Question → Test → Measure → Reflect → Improve

Every project must answer the same six questions:

  1. The Why: Why are we doing this?
  2. What problem am I trying to solve?
  3. Why does this matter in financial markets?
  4. How did I test it?
  5. What did I learn?
  6. What would I improve next?
  7. What is the bigger picture?

This structure keeps the work understandable to humans while preserving the technical evidence needed for reproducibility.

Repository roadmap

quant-lab/
├── README.md
├── 01-trader-toolkit/
│   ├── 01-trade-calculator/
│   ├── 02-options-analytics/
│   ├── 03-relative-value-screener/
│   ├── 04-market-maker-simulator/
│   ├── 05-bond-analytics/
│   └── 06-securities-financing-lab/
├── 01-python-foundations/
├── 02-financial-data/
│   └── moving-average-backtester/
├── 03-event-driven/
│   └── corporate-actions-borrow-rv-monitor/
├── market_basket_monitor/
├── 04-quant-research/
├── white-papers/
└── datasets/

Folders will be added as completed work becomes ready to publish. Empty categories are shown here as the intended roadmap rather than being populated with placeholder projects.

Published projects

01 — Trader Toolkit

Trader Toolkit target

The Trader Toolkit is being developed as a defined collection:

  1. Trade & Risk Analytics Calculator — complete
  2. Black-Scholes Options Analytics — complete
  3. Credit Relative Value Screener — complete
  4. Market Maker Simulator — complete
  5. Bond Pricing, Yield & Duration — complete
  6. Equity Borrow & Financing Scenario Lab — complete
  7. Value-at-Risk & Stress Testing — planned
  8. Pairs Trading & Cointegration — planned
  9. Order Book & Liquidity Analyzer — planned
  10. Portfolio Optimizer — planned
  11. Yield Curve & Forward Rate Analyzer — planned

02 — Financial Data

  • Project 1: SPY 50/200 Moving-Average Backtester — a bias-aware, cost-aware comparison of a simple trend-following rule with continuously holding SPY. 2005–2025: Sharpe 0.68 versus 0.63; annualised return 8.69% versus 10.66%; maximum drawdown −33.72% versus −55.19%. Strategy includes 5 bp costs per position change; Sharpe uses 0% risk-free.
  • Market Basket Monitor — a configurable macOS workflow for market-price alerts, news monitoring, weekly reporting and an automatically maintained Excel dashboard.

03 — Event-Driven Research

  • Corporate Actions, Borrow & Relative-Value Monitor — a risk-first Streamlit workflow connecting earnings and corporate events with inventory pressure, borrow-aware economics, seven-day and one-month horizons, scenario heatmaps and a review-ready daily briefing.

04 — Quant Research

  • Systematic Credit Momentum & Portfolio Construction — completed ETF research implementation with monthly signals, inverse-volatility sizing, credit caps, Treasury allocation, drift-aware transaction costs and auditable holdings. May 2008–December 2025: Sharpe versus SHY 0.70 versus 0.39 for HYG buy-and-hold; annualised return 4.23% versus 5.14%; month-end maximum drawdown −7.31% versus −29.92%. The 2016–2025 subperiod favours HYG on Sharpe; full-sample risk reduction does not establish persistent alpha.

Standards

  • Research questions and assumptions are stated before conclusions.
  • Signals are implemented without look-ahead bias.
  • Transaction costs and limitations are made visible.
  • Automated tests protect important calculations.
  • Negative results are retained when they are informative.
  • Plain-English explanations accompany technical outputs.

The material in this repository is historical research and education, not investment advice or a claim of future performance.

About

Quantitative finance research in Python: bias-aware backtests, credit and cross-asset analysis, portfolio risk and reproducible investment workflows

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages