UK Edition 19 November 2026 Independent · Editorial · No paid placements

AI in Trading

Artificial intelligence now touches almost every part of the trading workflow, from reading filings to monitoring systems. This hub collects our coverage of AI agents, language models and machine-learning analytics — with an emphasis on what works, what does not, and how to evaluate claims.

Articles

Analysis & guides

Directory

Relevant profiles

Full directory →

FinRobot

Agent framework

  • AI Agents & LLMs
  • Open-source

Open-source platform from the AI4Finance Foundation that orchestrates LLM-based agents for financial analysis tasks such as equity research reports and forecasting workflows.

Asset coverage
Equities, multi-asset research
Intended autonomy
Human-in-the-loop
Editorial note

Best viewed as a research scaffold rather than a finished product. Teams with Python experience can adapt its agent roles to their own data; outputs still require analyst review.

Official project / vendor site ↗

Full profile →

FinGPT

Financial LLM project

  • AI Agents & LLMs
  • Open-source

Open-source financial language models and data pipelines focused on lightweight fine-tuning for tasks such as sentiment classification and financial Q&A.

Asset coverage
News, filings, sentiment
Intended autonomy
Human-in-the-loop
Editorial note

Useful for experimentation with domain-adapted language models. Benchmark claims should be reproduced on your own data before being relied on.

Official project / vendor site ↗

Full profile →

Trade Ideas

Scanning platform

  • AI Analytics
  • Closed-source

Real-time stock scanning platform; its 'Holly' AI component runs strategy simulations overnight and surfaces candidate setups for the trading day.

Asset coverage
US equities
Intended autonomy
Semi-automated
Editorial note

Geared to active US equity traders. Published simulation results are not the same as live performance.

Official project / vendor site ↗

Full profile →

Intellectia.AI

AI research assistant

  • AI Analytics
  • Closed-source

AI-driven research assistant offering stock and crypto screeners, signals and summarised analysis.

Asset coverage
Equities, crypto
Intended autonomy
Human-in-the-loop
Editorial note

Treat signals as research prompts, not instructions. Methodology disclosure is limited, as with most closed-source signal products.

Official project / vendor site ↗

Full profile →

LevelFields AI

Event-analysis platform

  • AI Analytics
  • Closed-source

Scans news and corporate events such as buybacks or leadership changes and shows how stocks historically reacted to similar events.

Asset coverage
US equities
Intended autonomy
Human-in-the-loop
Editorial note

Event-study framing is useful context. Historical reactions vary widely, and small samples deserve caution.

Official project / vendor site ↗

Full profile →

Danelfin

AI scoring platform

  • AI Analytics
  • Closed-source

Assigns machine-learning-based scores to stocks and ETFs from technical, fundamental and sentiment features, with feature-level explanations.

Asset coverage
US & European equities, ETFs
Intended autonomy
Human-in-the-loop
Editorial note

The explanation of feature contributions is a welcome transparency step. Scores are probabilistic and should not stand alone.

Official project / vendor site ↗

Full profile →

Reference

Key terms

Agentic AI
Software that pursues a goal by planning steps, calling tools or data sources, and adjusting based on results, rather than answering a single prompt.
Hallucination
When a language model produces fluent but unsupported or false statements. A central risk when LLMs summarise financial documents.
Overfitting
Tuning a model so closely to historical noise that it fails on new data. The most common reason promising backtests disappoint live.