# ProsusAI/finBERT

Financial Sentiment Analysis with BERT

Repository: https://github.com/ProsusAI/finBERT
Canonical: https://ross.abutalabs.com/products/finbert
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2022-09-09T20:15:11+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2499, "days_push": 1454, "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 2217, forks 538 (observed 2026-08-28T04:06:27.247934+00:00)

## What it is
FinBERT is a pre-trained BERT language model further trained on financial text and fine-tuned for financial sentiment classification. It is distributed as a Python/Jupyter codebase with model weights on the Hugging Face model hub.

## Use cases
- analyze sentiment of financial news headlines
- classify sentiment of earnings call or report text
- score financial phrases as positive, negative, or neutral
- run sentiment analysis on stock market news with BERT
- fine-tune a language model on finance domain corpora
- use a pretrained financial NLP model in Python

## When to choose
- you need sentiment analysis specialized for financial text
- you want a ready-to-use pretrained model from the Hugging Face hub
- you work in Python with PyTorch and can manage a conda environment

## When to avoid
- you need general-purpose sentiment analysis outside the finance domain
- you require the modern transformers API, since this repo still depends on the older pytorch_pretrained_bert library
- you need actively maintained code with recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, fintech, artificial-intelligence
- platform: python
- tags: bert, sentiment-analysis, finance, hugging-face, pytorch, pretrained-model, natural-language-processing

## Member repositories
- ProsusAI/finBERT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.247934+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 2026-08-30T02:45:55.276811+00:00, confidence not recorded.
  - readme: https://github.com/ProsusAI/finBERT (fetched 2026-08-28T04:06:27.247934+00:00, sha 63f52c2d6f2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.