https://github.com/rowentey/stock-price

Visualize stock market predictions, STONKS! 📈
https://github.com/rowentey/stock-price

machine-learning python tensorflow

Last synced: 3 months ago
JSON representation

Visualize stock market predictions, STONKS! 📈

• Host: GitHub
• URL: https://github.com/rowentey/stock-price
• Owner: RowenTey
• License: mit
• Created: 2022-01-19T01:30:36.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2022-10-11T11:40:18.000Z (over 3 years ago)
• Last Synced: 2025-10-05T02:24:58.650Z (9 months ago)
• Topics: machine-learning, python, tensorflow
• Language: Python
• Homepage: https://share.streamlit.io/rowentey/stock-price/main/app.py
• Size: 373 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# 📈 Stock-Price-Predictor 

> *A web app that allows users to predict stock prices using LSTM and compare them to actual prices, STONKS 📈*

## 🧪 Tech 

This website is fully coded with Python, utilising the `Streamlit` module to structure our web app.  

The `Matplotlib` library was also used to visualize our data and construct our charts.

Our stock price prediction model is LSTM, built using Data Science and Machine Learning libraries like `Numpy`, `Pandas`, `Keras` and `Tensorflow`. 

## ❓ Assignment

*Problem Statement*: Current LSTM price prediction models can be easily thrown off by black swan events akin to Covid-19.

*Our Solution*: We hypothesise that black swan events are characterised by sudden spikes in trading volume. For example, when there is rapid buying or selling in a short amount of time. Our app allows students, professionals and enthusiasts alike to study the relationship between trade volume and the accuracy of LSTM predictions relative to actual prices.

## ⚙ How To Use

1. First, type in the **ticker** symbol you're looking for.  

2. Next, click the arrow icon on the top left corner. This opens up a sidebar. Select the date you 3. wish to start predicting the stock price from.  

4. Give a moment for the model to process your input.  

5. And that's it! The prediction will appear magically before your eyes. It's that **easy**!