This project involves building a stock portfolio management system using machine learning techniques for optimization and prediction. It combines clustering, risk-return optimization, and time-series forecasting, all integrated into an interactive Flask web application. The system empowers everyday investors with accessible, data-driven financial insights for better decision-making.
Key Components:
1.Portfolio selection and construction using clustering algorithm : K-means, Apriori
2.Portfolio optimization through Particle Swarm Optimization (PSO), Genetic Algorithms (GA), Simulated Annealing (SA)
- Forecasting portfolio weights using LSTM
Goals:
Please find the video here, https://github.com/SwetaAIS2024/IRS-PM-2024-10-27-AIS06FT-GRP-GROUP10/tree/master/Video
- Installation
Prerequisites:
- Python 3.8 or higher
- Flask
- Necessary libraries (e.g., TensorFlow, NumPy, Pandas)
Steps:
-
Clone the repository
-
Navigate to the System code and download the flask_implementation file
-
Unzip the file.
-
Install dependencies: pip install -r requirements.txt
-
Start the Flask server: python app.py
-
Open the application in a browser at
http://127.0.0.1:5000. -
User Guide
Navigating the Application: Home Page: Enter investment amount and choose between "Low-Risk" or "High-Return" portfolio strategies. Result Page: Review predicted returns and suggested stock allocations.
Features: Portfolio Strategy Selection: Choose between risk-focused or return-focused approaches. Investment Allocation: Suggested allocation based on the selected strategy.
Error Handling: If inputs are invalid or missing, clear messages will guide users to enter valid values.
Refer to project report at Github Folder: ProjectReport
** Sections for Project Report / Paper:**
- Executive Summary / Paper Abstract
- Business Problem Background
- Market Research
- Project Objectives & Success Measurements
- Project Solution
- Project Implementation
- Project Performance & Validation
- Project Conclusions: Findings & Recommendation
- Appendix of report: Project Proposal
- Appendix of report: Mapped System Functionalities against knowledge, techniques and skills of modular courses: MR, RS, CGS
- Appendix of report: Installation and Use
Refer to Github Folder: Miscellaneous
This Machine Reasoning (MR) course is part of the Analytics and Intelligent Systems and Graduate Certificate in Intelligent Reasoning Systems (IRS) series offered by NUS-ISS.
Lecturer: GU Zhan (Sam)
