Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,6 @@
|
|
| 3 |
This repository contains implementations of **time-series forecasting** for stock prices using both **traditional statistical models (ARIMA, Prophet)** and **deep learning (LSTM)**.
|
| 4 |
The project demonstrates model comparison, rolling-window evaluation, and deployment to Hugging Face Hub.
|
| 5 |
|
| 6 |
-
---
|
| 7 |
|
| 8 |
## Project Overview
|
| 9 |
- **Dataset**: Daily stock price dataset (closing prices).
|
|
@@ -17,7 +16,6 @@ The project demonstrates model comparison, rolling-window evaluation, and deploy
|
|
| 17 |
- **Deployment**:
|
| 18 |
- Models and results shared on Hugging Face Hub.
|
| 19 |
|
| 20 |
-
---
|
| 21 |
|
| 22 |
## Repository Contents
|
| 23 |
- `lstm_model.h5` – Trained LSTM model
|
|
@@ -26,7 +24,6 @@ The project demonstrates model comparison, rolling-window evaluation, and deploy
|
|
| 26 |
- `stock_forecasting_notebook.ipynb` – Full notebook with preprocessing, training, evaluation, and plots
|
| 27 |
- `upload_to_hf.py` – Script for uploading to Hugging Face Hub
|
| 28 |
|
| 29 |
-
---
|
| 30 |
|
| 31 |
## Quick start
|
| 32 |
1. Create and activate a python environment (recommended: conda or venv)
|
|
|
|
| 3 |
This repository contains implementations of **time-series forecasting** for stock prices using both **traditional statistical models (ARIMA, Prophet)** and **deep learning (LSTM)**.
|
| 4 |
The project demonstrates model comparison, rolling-window evaluation, and deployment to Hugging Face Hub.
|
| 5 |
|
|
|
|
| 6 |
|
| 7 |
## Project Overview
|
| 8 |
- **Dataset**: Daily stock price dataset (closing prices).
|
|
|
|
| 16 |
- **Deployment**:
|
| 17 |
- Models and results shared on Hugging Face Hub.
|
| 18 |
|
|
|
|
| 19 |
|
| 20 |
## Repository Contents
|
| 21 |
- `lstm_model.h5` – Trained LSTM model
|
|
|
|
| 24 |
- `stock_forecasting_notebook.ipynb` – Full notebook with preprocessing, training, evaluation, and plots
|
| 25 |
- `upload_to_hf.py` – Script for uploading to Hugging Face Hub
|
| 26 |
|
|
|
|
| 27 |
|
| 28 |
## Quick start
|
| 29 |
1. Create and activate a python environment (recommended: conda or venv)
|