# AlphaFin-proj/AlphaFin

Repository: https://github.com/AlphaFin-proj/AlphaFin
Canonical: https://ross.abutalabs.com/products/alphafin
Language: Python
License: MIT
License Family: permissive
Last push: 2026-04-03T05:01:20+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 75, release rhythm 35, longevity 64
- inputs: {"age_days": 899, "days_push": 152, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1029, forks 89 (observed 2026-08-28T04:03:17.729459+00:00)

## What it is
AlphaFin is a financial analysis benchmark dataset plus StockGPT chat models and the Stock-Chain retrieval-augmented framework, targeting stock trend prediction and financial Q&A. It combines research datasets, real-time financial data, and handwritten chain-of-thought data to reduce LLM hallucination in financial analysis.

## Use cases
- benchmark llms on financial analysis tasks
- fine-tune a model for stock trend prediction
- build a retrieval-augmented financial q&a chatbot
- reduce hallucination in llm financial answers
- train on financial reports with chain-of-thought data
- run rag over real-time stock data

## When to choose
- you need a benchmark for financial llm research
- you want to fine-tune an open model on financial reports
- you are building a rag-based stock analysis assistant
- you need cot training data for financial q&a

## When to avoid
- you need production financial advice or trading signals
- you need a non-research licensed product
- you need real-time low-latency trading infrastructure
- you work outside the financial domain

## Facets
- artifact type: dataset
- maturity: active
- function: rag, machine-learning, llm-training, data-science
- domain: fintech, large-language-models, machine-learning
- platform: python
- tags: financial-analysis, stock-trend-prediction, financial-qa, stockgpt, stock-chain, fine-tuning, chain-of-thought, benchmark, retrieval-augmented-generation

## Member repositories
- AlphaFin-proj/AlphaFin (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.729459+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:07:36.795832+00:00, confidence not recorded.
  - readme: https://github.com/AlphaFin-proj/AlphaFin (fetched 2026-08-28T04:03:17.729459+00:00, sha 1940041b14f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.