https://github.com/samadpls/stockseer-api
Fast-API base StockSeer-API uses different machine learning alogs to forecast closing stock prices.
https://github.com/samadpls/stockseer-api
extratreesregressor fastapi kneighborsclassifier linear-regression lstm machine-learning-algorithms open-source random-forest stock-price-prediction
Last synced: 12 months ago
JSON representation
Fast-API base StockSeer-API uses different machine learning alogs to forecast closing stock prices.
- Host: GitHub
- URL: https://github.com/samadpls/stockseer-api
- Owner: samadpls
- License: mit
- Created: 2024-05-14T18:45:10.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-11-02T14:33:27.000Z (over 1 year ago)
- Last Synced: 2025-04-02T20:45:09.336Z (about 1 year ago)
- Topics: extratreesregressor, fastapi, kneighborsclassifier, linear-regression, lstm, machine-learning-algorithms, open-source, random-forest, stock-price-prediction
- Language: Python
- Homepage:
- Size: 237 KB
- Stars: 11
- Watchers: 1
- Forks: 4
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## StockSeer-API `(Stock Price Prediction API)`


[](https://github.com/psf/black)
[](LICENSE)
This project is a FastAPI application that predicts the closing stock price for a given company based on user-specified parameters. It utilizes various machine learning models for prediction, including:
* RandomForestRegressor 🌳
* ExtraTreesRegressor 🌲
* LinearRegression ➖
* KNeighborsRegressor 🤝
* LSTM implementation 🔄
## Data Source:
This application utilizes the Yahoo Finance API to retrieve historical stock data for training and prediction purposes.
## Features✨
* Download and preprocess historical stock data
* Train a stock price prediction model of your choice
* Make predictions on future closing stock prices
## Working Prototype
**Example: Predicting
oogle
Stock Price**
| Input | Response|
raph |
|------|---------|---------|
|||
|
## Installation
1. Ensure you have Python installed.
2. Create a new virtual environment (recommended).
3. Activate the virtual environment.
4. Install required dependencies:
```bash
pip install -r requirements.txt
```
## Usage
1. Run the application:
```bash
uvicorn app:app --reload
```
2. Access the API documentation in your web browser: http://127.0.0.1:8000/docs
The documentation provides instructions on interacting with the API to make predictions.
## Credits
* **Maira Usman:** Developed the GUI for this project. You can find the code here: Link to [StockSeer-Frontend](https://github.com/Myrausman/StockSeer-Frontend).
## Disclaimer
**Important:** Stock price prediction is inherently uncertain. This application should not be used for making financial decisions.