Link To The Original Github Repository Of The Code: GitHub Repository
Link To The Data Repository: Data Repository
Link To Wordpress Website Showing Project Information: Word Press Website
Link To Video Demo: Final Year Project Video
Link To The Poster: Project Poster
Link To The Presentation: Project Presentation
Author: Masood Ahmed
Email: [email protected]
Author: Aryan Agarwal
Email: [email protected]
Author: Arnav Rajiv
Email: [email protected]
| Javascript | React Js | Tensorflow (Python) | PyTorch (Python) | Flask (Python) | FinRL | SQLAlchemy | LLaMA-2 |
|
|
|
|
|
|
|
|
Note: Node and Python should be installed in your machine before proceeding!
- Step 1: Navigate to client-v1 and run the following commands:
cd client-v1
npm install
npm start- Step 2: Navigate to stock-forecasting-server and run the following commands:
cd ../stock-forecasting-server
npm install -g serve
serve -l 8000-
Step 3: Export API keys your respective OS
On Windows: - Open the Start menu and search for "Environment Variables". - Select "Edit the system environment variables". - Click on the "Environment Variables" button. - In the "System Variables" section, click on "New" to add a new environment variable. - Enter the name of the variable (i.e.., OPENAI_API_KEY, and FINNHUB_API_KEY) and its corresponding value (e.g., your API key). - Click "OK" to save the changes. On macOS or Linux: - Open a terminal window. - Type export OPENAI_API_KEY="your_api_key" and press Enter - Type export FINNHUB_API_KEY="your_api_key" and press Enter - Replace "your_api_key" with your actual API key. -
Step 4: Navigate to server and run the following commands:
cd server
pip install -r requirements.txt
python3 -m flask --app server.py runNote: This method only works if you have setup the project before .i.e. have followed method 1 atleast once.
- Step 1: Stay in the root folder
chmod +x run.sh (You need to do this once)
./run.shCheck out our contributing guidelines for ways to offer feedback and contribute.
For providing funding and support to this project, please reach out to [email protected] or [email protected] or at https://www.linkedin.com/in/masood/. Any kind of support and funding is appreciated.
- API Endpoints Documentation
- Deep Learning Models Documentation
- Trading Agnets Documentation
- FinLLM Documentation
- Registration Page and Login Page (allows users to register using their username, email address, and password and login with email address + password + username.)
- Can interact with other users on the discussion forum and talk about the financial market and strategies.
- Can look and run deep learning agents with different parameters on the choosen stock data (OHLCV). Here is a sample data: Google. This will allow them see how each deep learning algorithm works on stocks by showing them Epoch Loss Curve and Price Prediction Graphs.
- Trading Agents: Multiple different trading agents are available to the user to choose from which can be used by the user to make predictions on the choosen stock data and find buy and sell points.
- FinLLM: A Large Language Model trained on financial data to provide positive developments, potential concerns, summary, prediction & anlysis and news related to the choosen stock. (NOTE: In order to use this feature, you need to have a valid API key for the OpenAI API. You also need to have a valid Finnhub API Key as well.The API key is used to authenticate and access the Finnhub API. You can sign up and obtain an API key from the Finnhub website.) A traditional LLAMA model is also available to the user to provide detailed analysis of the chosen stock, however, the performance of GPT 3.5 was much better. Therefore, current version of the application makes use of GPT 3.5.
Pull requests are welcome. For feedback and suggestions, please reach out to Group fyp23070 at the following email: [email protected] or at any of the above author emails provided.
COMP4801 Group fyp23070 2024 © The University of Hong Kong