Stock Exchange Prediction using Machine Learning

Video

Below is the video which describes our project's idea and implementation

Why choose this project:

• The project provides visualisation of stocks of 2000+ company markets and helps in making prediction for the next time period.
• Modular architecture
• Scalable design
• You will be able to explore data analysis, predictive modelling and explore the integration of NLP functionality.
• You can scale the project to use different predictive models to compare the efficiencies as well as compare different stocks to make the right decision to invest.

Technologies and Tools

Language: Python 3, HTML, CSS

Libraries: Flask, click, yfinance, matplotlib, Werkzeug, pandas, numpy, get_all_tickers, pytest, scikit_learn.

Web Application Framework: Flask

Test Framework: pytest

Database: SQLite

Tools: Visual Studio Code

Syntax Checker & Sytle Checker: pylint (VSCode Python v2020.8.109390 Extension)

Code Formatter: autopep8 (VSCode Python-autopep8 v1.0.2)

Version Control: git

Installation Guide

Using Docker

1. navigate to the project directory with the Dockerfile
2. docker build -t csc510/p1:latest .
3. docker run -p 5000:5000 csc510/p1:latest
4. open browser and enter http://localhost:5000/auth/login

For Mac/Ubuntu

Install Flask using pip - pip/pip3 install flask

cd to project directory

export FLASK_APP=flaskr

flask init-db

For Windows

Install Flask using pip - pip/pip3 install flask

cd to project directory

set FLASK_APP=flaskr

flask init-db

Run

To run just do the following

flask run

Application Overview

Database Schema