Resources

📚 Books & Textbooks

1. Advances in Financial Machine Learning – Marcos López de Prado

   • The quant bible. Dense, but very relevant for hedge-fund-grade ML.

2. Machine Learning for Asset Managers – Marcos López de Prado

   • Slim, practical, easier-to-digest version of the above.

3. Machine Learning in Finance – Matthew Dixon, Igor Halperin, Paul Bilokon

   • Academic, deep, Python-heavy.

4. Artificial Intelligence in Asset Management – CFA Institute Research Foundation

   • Free PDF from CFA Institute. Very digestible and practical.

5. Python for Finance – Yves Hilpisch

   • Focuses more on time series, derivatives, and trading systems.

6. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow – Aurélien Géron

   • Not finance-specific, but absolutely essential for mastering ML pipelines.

---

🎓 Online Courses (Free + Paid)

1. AI in Finance Specialization – CFTE (Paid)

   • Practical AI tools for asset management, trading, and compliance.

2. Financial Engineering & Risk Management – Columbia (Coursera) (Free/Paid)

   • Not pure ML, but very quantitative.

3. Machine Learning for Trading – Georgia Tech (Udacity) (Free/Paid)

   • One of the OG courses for quants.

4. AI for Trading – Udacity Nanodegree (Paid)

   • Focuses on NLP, RL, and trading signals.

5. Applied Machine Learning in Python – University of Michigan (Coursera)

   • Covers regression, classification, clustering (not finance-focused, but applicable).

6. YouTube Channels:

   • QuantInsti, QuantPy, Ken Jee, Sentdex, QuantLayer, PyQuant News

---

🧪 GitHub Projects & Code Repos

1. Hudson-and-Thames/mlfinlab

   • Implements López de Prado’s techniques. Very detailed.

2. OpenBBTerminal

   • Like Bloomberg Terminal for Python nerds. Open-source.

3. AI4Finance-Foundation/FinRL

   • Reinforcement learning for trading strategies.

4. yfinance

   • Not ML, but essential for stock data in finance models.

5. QuantConnect/Lean

   • Full algorithmic trading platform (C#/Python), can plug in ML.

6. pmorissette/bt

   • Framework for backtesting portfolios with some ML plug-in ability.

---

📂 Datasets for Finance + ML

1. Yahoo Finance (via yfinance)

   • Stocks, indices, historical prices.

2. Quandl (now Nasdaq Data Link)

   • Macroeconomic, futures, commodities, alt data.

3. NSE/BSE data (India)

   • Use nsetools, nsepy, or scrape directly.

4. Kaggle Datasets

   • Search “finance,” “stock,” “options,” “credit scoring,” etc.

5. FRED (Federal Reserve Economic Data)

   • Macroeconomic indicators, interest rates, inflation, etc.

6. Alpaca API / IEX Cloud / Alpha Vantage / Twelve Data

   • APIs with free tiers for stock/crypto/forex data.

7. SEC EDGAR + Screener.in + TickerTape.in

   • For Indian filings, financial statements, ratios (requires scraping/API work)

---

🧠 Research Papers & Journals

1. arXiv.org – Quantitative Finance

   • Constant stream of fresh research (ML + finance papers weekly).

2. SSRN Financial AI Papers

   • Search for "AI in Finance" or "Machine Learning Trading."

3. Journal of Financial Data Science (JFDS)

   • Published by CFA Institute and Portfolio Management Research.

---

🧰 Tools & Platforms

1. Streamlit – For building apps/dashboards.

2. Jupyter Notebooks – Standard for finance prototyping.

3. Power BI / Tableau – For final dashboards, fed by Python.

4. Google Colab – Cloud-based Python notebook (no setup).

5. OpenAI GPT API – For commentary, summarization, chat-based assistants.

6. Bloomberg Terminal (if you're rich) – For actual finance workflows.

7. Excel VBA + Python – For hybrid automation (ugh, but useful).