@Huanusa: This is absolutely mind-blowing! Someone actually built an AI that can directly read candlestick trading, and its performance is through the roof! It's called Kronos — the world's first open-source foundational large model designed specifically for financial markets! Trained from scratch on 12 billion real candlestick data points from 45 exchanges, not a repurposed general AI. It can: price prediction + volatility prediction and more.
Summary
Kronos is the world's first open-source foundational large model for financial markets, trained from scratch on 12 billion real candlestick data points, supporting price prediction and volatility forecasting, far outperforming general models, and completely free and open-source.
View Cached Full Text
Cached at: 05/14/26, 10:34 AM
Kronos: A Foundation Model for the Language of Financial Markets
📜 Introduction
Kronos is a family of decoder-only foundation models, pre-trained specifically for the “language” of financial markets—K-line sequences. Unlike general-purpose TSFMs, Kronos is designed to handle the unique, high-noise characteristics of financial data. It leverages a novel two-stage framework:
- A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens.
- A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.
Similar Articles
Kronos: A Foundation Model for the Language of Financial Markets
Kronos is a new foundation model for financial K-line data that uses a specialized tokenizer and autoregressive pre-training to outperform existing models in forecasting and synthetic data generation.
shiyu-coder/Kronos
Kronos is an open-source foundation model for financial K-line sequences, trained on data from over 45 global exchanges. It uses a specialized tokenizer and a decoder-only Transformer, and has been accepted at AAAI 2026.
@FinanceYF5: 10 Ready-to-Use Financial AI Agent Templates — Claude for Finance Means Business. Anthropic Releases 10 Out-of-the-Box Financial AI Agent Templates Covering Pitch Books, KYC, Valuation Reviews, Financial Models, Month-End Close, and More.
Anthropic has released 10 ready-to-use financial AI agent templates covering a wide range of financial use cases, including pitch books, KYC, valuation reviews, financial models, and month-end close.
@cyrilXBT: CHINA JUST BUILT AN AI MODEL THAT IS COMPETING WITH OPENAI AND ANTHROPIC AT A FRACTION OF THE COST. And someone just dr…
DeepSeek, a Chinese AI model built by a quant hedge fund, is reportedly competing with GPT-4 level performance at roughly 5% of the training cost, causing significant market disruption including a $600B drop in NVIDIA's market cap. A free 1 hour 50 minute course has been released teaching users how to leverage DeepSeek V4 locally and via API.
@rwayne: Anthropic has essentially laid out the investment banking workflow directly on GitHub. The official repository anthropics/financial-services was launched 11 weeks ago, garnering 16,493 stars and 2,067 forks. It includes 9 out-of-the-box Agents, including Pitch…
Anthropic has open-sourced the financial-services repository, offering 9 out-of-the-box AI agents for investment banking and 11 MCP data connectors, aiming to automate workflows such as financial modeling, research report writing, and compliance reviews.