MarketSenseAI 2.0: Stock Analysis through LLM Agents
arxiv.orgLLM-agent framework combining fundamentals, news and macro signals for stock analysis.
- Published
- Feb 1, 2025
- Authors
- 4
DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 2,629–2,664 of 14,444 resources
LLM-agent framework combining fundamentals, news and macro signals for stock analysis.
Studies LLM-based stock trading behaviour inside simulated real-world market environments.
Bilingual Chinese-English benchmark for evaluating financial large language models.
Instruction-tunes a large language model on financial data to answer investment questions.
End-to-end causal discovery model for news-driven stock movement prediction.
Combines graph relations with a Mamba state-space model for stock movement prediction.
Multi-graph convolution exploiting sector and supply-chain relations for stock prediction.
Hierarchical graph attention network predicting stock movement from relational data.
PPO-based adaptive weighting of LLM-generated alpha factors in quantitative trading.
Constructs a Japanese financial benchmark for evaluating large language models.
Japanese financial instruction dataset for adapting LLMs to Japanese finance tasks.
Introduces event-level financial sentiment analysis with a new annotated benchmark.
Adversarial training of an attentive LSTM for stock prediction from prices and tweets.
Applies deep reinforcement learning to continuous-action stock portfolio optimisation.
LLM-driven pipeline that automatically discovers and validates quantitative strategies.
Uses large language models with chain-of-thought to mine alpha factors in quant trading.
Adapts an open LLM to Dutch financial text and evaluates it on domain tasks.
Domain-adapted language model for sentiment extraction from bond-market text.
Case study combining multimodal data for stock price prediction on the Russian market.
Uses ChatGPT-derived relation strengths to build a GNN for stock movement prediction.
module to get data from various sources (Google Finance, Yahoo Finance, FRED, OECD, Fama/French, World Bank, Eurostat...) into Pandas datastructures such as…
The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
pysystemtrade is the open source version of Robert Carver's backtesting and trading engine that implements systems according to the framework outlined in his…
Financial portfolio optimization in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity.
Wealth management software to keep track of financial assets like stocks, ETFs or cryptocurrencies and make solid, data-driven investment decisions
A python bot that lets you trade in most crypto exchanges and allows you to optimize your strategies with machine learning.
Satellite-derived maritime AIS, aviation and weather data services for analytics.
Real-Time and historical market data via HTTP and Websocket
Live leaderboard and benchmark dataset for evaluating AI-generated image detectors. Real-time rankings updated as new detectors are evaluated against 2,038…
Real-time weather data in a free or paid API
Certstream provides a publicly accessible real‐time feed of certificate transparency logs, delivering live updates on SSL/TLS certificate issuance as it occurs
Firehose is an authenticated stream of events on the protocol that underlies Bluesky, enabling efficient syncing of user updates via a WebSocket connection
A comprehensive suite of real-time, curated threat data streams that deliver actionable insights on malicious domains, IP addresses, URLs, file hashes, and…
This list is inspired by , but for real-time datasets and sources. Normally accessed via HTTP or Websockets
Data Bento provides low-latency market data from many exchanges in several schemas. Access over Raw API, which uses a binary protocol over TCP, and…
Coinbase Exchange WebSocket feed including level 2 order book and ticker channels.