---
title: Sita Sector Classifier
emoji: 🌍
colorFrom: green
colorTo: green
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
pinned: false
---

# Sita Sector Classifier

Gradio web UI for the fine-tuned DistilBERT sector classifier built by MC Studio (Christine Matinde and Stacey Nduta) for the IBM x MC Studio Program.

## What it does

Paste a company description and it predicts the most likely Sita Sector industry, with confidence.

## Model

- Model: `mcsqstudio/africa-sector-classifier` (DistilBERT fine-tuned on 7 sectors)
- Dataset: [mcsqstudio/africa-startup-directory](https://huggingface.co/datasets/mcsqstudio/africa-startup-directory)

## Sectors

| Code | Sector |
| ---- | ------ |
| ATX | Agritech |
| ETX | Edtech |
| HTX | Healthtech |
| FTX | Fintech |
| REC | Retail & E-commerce |
| ERG | Energy |
| MFG | Manufacturing |

## Note

This Space activates the model lazily on first use. If it reports that the model is not ready, run `Sita_Sector_Model_v2_transformers.ipynb` in Colab to fine-tune and push the model, then click Classify again.