ML-Quant
Built for agents too.
Every page has a Markdown twin, the site has an index for language models, and the data is one GET away. No key, no login, no scraping needed.
Start here
Paste this into Claude, ChatGPT or any agent that can read the web:
Use ML-Quant (https://www.ml-quant.com/llms.txt) to find the most-cited machine-learning-for-finance papers featured since 2024 on volatility forecasting, and summarise what they found.
llms.txt
The site index for language models: what ML-Quant is, and links to the Markdown version of every section. Open it or copy it:
# ML-Quant > ML-Quant ranks new research on machine learning in quantitative finance every week. Each Friday it screens every new arXiv, SSRN and RePEc paper, ranks the best 30 per venue with a one-sentence summary and the paper's key figure, tracks every featured paper's citations and journal publication on Semantic Scholar, and reports what about 10,600 quant developers starred on GitHub. 132 issues since May 2023; 6,396 featured papers. Every page has a Markdown twin: append `index.md` to its URL. Our summaries are CC BY 4.0; please link back. JSON for everything: https://www.ml-quant.com/api/v1/index.json ## This week - [Quant Letter No. 132, 2026-09-25](https://www.ml-quant.com/issues/2026-09-25/index.md): 90 ranked papers with summaries, top picks, rising topics, GitHub radar - [GitHub radar](https://www.ml-quant.com/radar/index.md): what quant developers starred this week - [Track record](https://www.ml-quant.com/track-record/index.md): what became of every featured paper (citations, journals) ## Topics - [Crypto & DeFi](https://www.ml-quant.com/topics/crypto-defi/index.md): 294 papers. Crypto assets, DeFi, stablecoins and blockchain markets. - [LLMs & Text](https://www.ml-quant.com/topics/llms-text/index.md): 577 papers. Large language models, agents, sentiment and text as data in finance. - [Derivatives & Volatility](https://www.ml-quant.com/topics/derivatives-volatility/index.md): 868 papers. Option pricing, volatility models and forecasting, hedging and implied surfaces. - [Trading, Microstructure & Execution](https://www.ml-quant.com/topics/trading-microstructure-execution/index.md): 538 papers. Order books, market making, execution, high-frequency data and trading signals. - [Portfolio & Allocation](https://www.ml-quant.com/topics/portfolio-allocation/index.md): 609 papers. Portfolio construction, allocation, rebalancing and risk budgeting, from Markowitz to deep RL. - [Risk, Credit & Banking](https://www.ml-quant.com/topics/risk-credit-banking/index.md): 363 papers. Credit risk, default prediction, banking, systemic risk and risk measures. - [Asset Pricing & Factors](https://www.ml-quant.com/topics/asset-pricing-factors/index.md): 249 papers. Factor models, anomalies, the cross-section of returns and what survives publication. - [Macro-Finance & Rates](https://www.ml-quant.com/topics/macro-finance-rates/index.md): 258 papers. Rates, the yield curve, monetary policy, inflation and macro-finance. - [Econometrics & Forecasting](https://www.ml-quant.com/topics/econometrics-forecasting/index.md): 297 papers. Forecasting, time series, econometrics and nowcasting. - [ML & AI Methods](https://www.ml-quant.com/topics/ml-ai-methods/index.md): 1107 papers. Machine-learning methods applied to finance: deep learning, boosting, RL and new architectures. - [Corporate Finance](https://www.ml-quant.com/topics/corporate-finance/index.md): 169 papers. Firms, governance, IPOs, M&A and corporate decisions. - [Other](https://www.ml-quant.com/topics/other/index.md): 1067 papers. Everything that doesn't fit the other topics: economics, policy and the odd surprise. ## Papers by venue - [arXiv](https://www.ml-quant.com/papers/arxiv/index.md): Quantitative-finance and ML-for-finance preprints from arXiv. - [SSRN](https://www.ml-quant.com/papers/ssrn/index.md): Working papers in finance and economics from SSRN. - [RePEc](https://www.ml-quant.com/papers/repec/index.md): Economics working papers from RePEc's NEP field reports. - [Machine learning](https://www.ml-quant.com/papers/ml/index.md): The general machine-learning papers the letter carried in 2023-25. ## Recent issues - [No. 132: September 2026, Week 4](https://www.ml-quant.com/issues/2026-09-25/index.md): 2026-09-25 - [No. 131: May 2026, Week 3](https://www.ml-quant.com/issues/2026-05-20/index.md): 2026-05-20 - [No. 130: April 2026, Week 3](https://www.ml-quant.com/issues/2026-04-16/index.md): 2026-04-16 - [No. 129: April 2026, Week 1](https://www.ml-quant.com/issues/2026-04-03/index.md): 2026-04-03 - [No. 128: March 2026, Week 1](https://www.ml-quant.com/issues/2026-03-04/index.md): 2026-03-04 - [No. 127: February 2026, Week 2](https://www.ml-quant.com/issues/2026-02-12/index.md): 2026-02-12 - [No. 126: February 2026, Week 1](https://www.ml-quant.com/issues/2026-02-02/index.md): 2026-02-02 - [No. 125: January 2026, Week 3](https://www.ml-quant.com/issues/2026-01-16/index.md): 2026-01-16 ## Data - [API index](https://www.ml-quant.com/api/v1/index.json): every endpoint - [OpenAPI](https://www.ml-quant.com/openapi.json) - [Track record data](https://www.ml-quant.com/api/v1/track-record.json) - [Search index](https://www.ml-quant.com/api/v1/search.json): every paper, topic, issue and repo in one file - [RSS](https://www.ml-quant.com/feed.xml) - [MCP server](https://www.ml-quant.com/mcp): Streamable HTTP, read-only, no auth ## Optional - [All issues](https://www.ml-quant.com/issues/index.md) - [Library](https://www.ml-quant.com/library/index.md): news, podcasts, blogs, videos, repos - [llms-full.txt](https://www.ml-quant.com/llms-full.txt): the latest issues and the track record in one file - [For agents](https://www.ml-quant.com/agents/index.md) - [About](https://www.ml-quant.com/about/index.md)
Longer context in one file: llms-full.txt (the latest issues and the track record).
Markdown twins
Every page has one: add index.md to the address (for example /track-record/index.md). Pages announce it with <link rel="alternate" type="text/markdown">, and the Copy for AI button on every page copies it.
MCP server
A read-only Model Context Protocol server, no login: search, papers, issues, topics, the radar and the track record as tools.
claude mcp add --transport http ml-quant https://www.ml-quant.com/mcp
Other clients: add a remote (Streamable HTTP) server with the URL https://www.ml-quant.com/mcp.
JSON API
Static files, CORS open, refreshed every Friday.
| Path | What |
|---|---|
/api/v1/index.json | Every endpoint, with counts |
/api/v1/issues.json | All issues: date, title, counts, links |
/api/v1/issues/{date}.json | One issue, every line |
/api/v1/papers/{venue}.json | Featured papers per venue: arxiv, ssrn, repec, ml |
/api/v1/topics/{slug}.json | A topic's papers and quarterly counts |
/api/v1/track-record.json | Every featured paper with citations and venue |
/api/v1/radar.json | This week's GitHub radar |
/api/v1/search.json | The compact search index the site uses |
/openapi.json | OpenAPI 3.1 description of the above |
Feeds
The letter (RSS) and one feed per topic, e.g. LLMs & Text.
Terms
Crawl, quote, and train on it: robots.txt says Content-Signal: search=yes, ai-input=yes, ai-train=yes. Our summaries are CC BY 4.0: please link back. Citation counts come from Semantic Scholar (ODC-BY). Paper abstracts belong to their authors; we only show arXiv's.