FinReasoning
github.comFrom Generation to Decision: A Hierarchical Benchmark for Reliable Financial Reasoning with LLMs
- GitHub stars
- 8
- Language
- Python
- Code license
- Apache-2.0
DUCKQUANT / THE QUANT & AI DIRECTORY
2,336 resources, ranked by in-directory PageRank
From Generation to Decision: A Hierarchical Benchmark for Reliable Financial Reasoning with LLMs
FinTagging: an LLM-ready benchmark for XBRL tagging of financial reports (arXiv:2505.20650)
Deep learning platform for financial forecasting: phased CNN, LSTM, transformer and TFT training pipelines whose models are served by prediction-provider
First Version.. Cryptocurrency Prediction with Artificial Intelligence (Deep Learning via LSTM Neural Networks)- Emirhan BULUT
CryptoCurrency prediction using machine learning and deep learning
Stock price movement prediction using artificial neural networks
Official code for "RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models"
Customize loss function by taking account of directional loss to make the LSTM model more applicable given limited resources
presents an in-depth exploration of a cutting-edge trading architecture that combines the predictive power of Long Short-Term Memory (LSTM) neural networks
Deep Learning - Neural network (RNN, LSTM & GRU)
Assay is a high-performance factor backtesting engine built for LLM agent-driven alpha mining
LLM-Powered Factor Mining and Evaluation Agent for Quantitative Research
This repository hosts an AI agent that autonomously researches quantitative trading strategies using machine learning. The agent analyzes datasets, experiments
Develop a quantitative trading algorithm using advanced financial forecasting and machine learning techniques. Explore methods like Bayesian estimation, neural
Can a machine learning model beat buy-and-hold on Indonesian stocks? This project builds, tests, and rigorously evaluates a trading strategy powered by XGBoost
Utilizando técnicas de Machine Learning e Deep Learning (IA), para o mercado financeiro
AI-powered XAUUSD (Gold) trading bot with XGBoost ML, Smart Money Concepts (SMC), and HMM regime detection for MetaTrader 5 xau ai trading bot gold…
Autonomous AI trading bot and digital assistant. Built for continuous market awareness and automated execution
I’ve just created my own bot and I’m excited to share my work with you!
AI-powered XAUUSD (Gold) trading bot with XGBoost ML, Smart Money Concepts (SMC), and HMM regime detection for MetaTrader 5
Design pattern for critical stages in the development process of an AI Stock Trading Bot
financial advisor LLM using llama 3.2 3B and RAG with PDF file compatibility
FinAgent-RAG: Agentic Retrieval-Augmented Generation for Financial Document Question Answering
RAG pipeline for Brazilian financial reports. Multi-agent system with LangGraph, hybrid search (Qdrant + BM25), structured outputs via Pydantic, FastAPI
MoziAI-35B: Local open-source financial AI LLM. 35B MoE model compressed to 15.5GB via MoziSmartBit quantization. 256K context, vision, tool calling, 140+
Open-source, privacy-first personal finance cockpit. Bring accounts, transactions, budgets, goals, assets & reports into one intelligent workspace — with
A hybrid RAG chatbot that answers financial and tax questions using structured data, regulatory documents, and AI-powered retrieval. Built with Django, FAISS
Developing a RAG-powered chatbot for CreditTrust Financial that analyzes customer complaints across five financial products. The AI tool retrieves relevant
Cutting-edge financial analysis tool using Retrieval-Augmented Generation (RAG) to process complex financial data. This project combines AI-powered document
An Interfernce RAG-based LLM Pipeline with Best Practice LLMOps
AutoQuantAI is an open source intelligent financial analysis platform integrating RAG, Algorithm Strategies,LLM,and Real-time Market Data (A-Share). It serves
A modular, multilingual, and multimodal Retrieval-Augmented Generation (RAG) system tailored for the financial analysis of Public Investment Fund (PIF) annual
Advanced RAG pipelines for medical (HealthBench, MedCaseReasoning, MetaMedQA, PubMedQA) and financial (FinanceBench, Earnings Calls) QA. LangGraph
LLM-powered financial analyst using LoRA-tuned Llama-3 and RAG pipeline to answer complex queries over SEC 10-K filings with contextual accuracy
Agentic RAG over 10-K filings with cited answers. LangGraph + Pathway. 1st place, Inter IIT Tech Meet 13.0
FinAuditing: a taxonomy-structured, multi-document auditing benchmark for LLMs (arXiv:2510.08886)