Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rhythm-shahane/trend-pulse
This repository implements LSTM for the purpose of stock prediction⬇️
https://github.com/rhythm-shahane/trend-pulse
altair lstm-model machine-learning prediction-model python quantitative-finance rapidminer stocks tesla
Last synced: 24 days ago
JSON representation
This repository implements LSTM for the purpose of stock prediction⬇️
- Host: GitHub
- URL: https://github.com/rhythm-shahane/trend-pulse
- Owner: Rhythm-shahane
- Created: 2024-02-11T13:34:10.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-02-22T12:16:48.000Z (9 months ago)
- Last Synced: 2024-06-11T06:58:58.405Z (5 months ago)
- Topics: altair, lstm-model, machine-learning, prediction-model, python, quantitative-finance, rapidminer, stocks, tesla
- Language: Jupyter Notebook
- Homepage: https://trend-pulse.streamlit.app/#tesla-stock-price-prediction
- Size: 312 KB
- Stars: 1
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 📈**Stock Prediction Model**
This repository implements LSTM is for the purpose of stock prediction.
### - Team Information:
Devansh Shahane (Team Lead)
- [Email ID: [email protected]](mailto:[email protected])
- [Linkedin ID: Devansh Shahane](https://www.linkedin.com/in/devansh-shahane/)
Prathamesh Sharma
- [Email ID: [email protected]](mailto:[email protected])
- [Linkedin ID: Prathamesh Sharma](www.linkedin.com/in/prathamesh-sharma/)
Nirbhay Tiwari
- [Email ID: [email protected]](mailto:[email protected])
- [Linkedin ID: Nirbhay Tiwari](https://www.linkedin.com/in/nirbhay-tiwari/)
## **Motto: " WE Got You Covered "**
# 📈 **Stock Prediction Model**
### **Predicting Stocks with ML**
**Stock Prediction Model is an ML-powered stock price prediction app built with Python and Streamlit. It utilizes machine learning models to forecast stock prices and help investors make data-driven decisions.**
# **👓 Quick OverView**
## **Model Deployment**
### - **Please check it over here: [📈Stock Prediction Model ](https://trend-pulse.streamlit.app/#tesla-stock-price-prediction)**
### - **To Run it effectively, with more crisp understanding: [Run On Google Colab](https://colab.research.google.com/github/Rhythm-shahane/Trend-Pulse/blob/main/Google_Colab.ipynb)**
### - **A Easier Presentation, has been linked here: [A Quickie](https://tome.app/rhythms-space-org/trend-pulse-navigating-tomorrows-markets-with-lstm-intelligence-clsknglyp08j6mu62chcpjx1a)**
# **📊Dataset Description**
The dataset provided is the historical stock market data of Tesla, Inc. (TSLA).
Here's a summary of its structure and key statistics:
## The Dataset Contains:
- Date: The date of the stock data, formatted as MM/DD/YYYY.
- Open: The price of the stock at the opening of the trading day.
- High: The highest price of the stock during the trading day.
- Low: The lowest price of the stock during the trading day.
- Close: The closing price of the stock for the trading day.
- Volume: The number of shares traded during the trading day.
- Adj Close: The adjusted closing price, accounting for any corporate actions such as dividends, stock splits, etc.
## Data Anaylsis:
### - There are 1,692 entries, indicating stock data for 1,692 trading days.
### - The dataset starts from June 29, 2010, with the first few entries showing significant volatility in the stock price and trading volume.
### - The Volume of shares traded also varies greatly, from as low as 118,500 to as high as 37,163,900, with a mean trading volume of around 4,270,741 shares.
## Dataset Split Info
The dataset is divided into training and validation sets as follows:
- **Training the model by some old data from the dataset.**
- **Validating data on the previous closing values from the dataset.**
- **Predicting data by using the trained model.**
# **💡Approach**
### 1. First The Model fetch Dataset File (with an ext of .csv)
### 2. Secondly the Model understands the Data Injection By Kaggle
### 3. Then the data is cleaned and then trained
### 4. Training model on the closing values of each day from the dataset file.
### 5. The Lib like Numpy manipulates the array, along side Lib Panda Transforms and Visualises the Data.
### 6. The Lib Matplot, it plots the data, along with plotty for more reactive graphs.
### 7. Using Keras, Sequential, Dense & the most prominent LSTM model, we train the model layer by layer.
### 8. At the last the Output has been trained on the older data from the CSV file.
### 9. The Trained model gives the predicted the plotting with the valid values,
### 10. Hence generated the final output of the next day closing value on the basis of previous 60 days.
# **🚀Results**
## Here are The entered dataset values :
## Here is the Final Result Graph:
## Here is the prediction for the closing Price of the next day:
# 🏗️ **Dependences**
Trend Pulse is built with these core frameworks and modules:
- **Streamlit** - To create the web app UI and interactivity
- **LSTM** - To build the Long Short Term Memory model
- **Plotly** - To create interactive financial charts
# ⛩️ **Workflow**
The app workflow is:
1. User feeds the CSV file.
2. Historical data is fetched with CSV file.
3. LSTM model is trained on the data
4. Model makes multi-day price forecasts
5. Results are plotted with Plotly
# ➼ **Accuracy**
## We Use Root Mean Square Deviation:
### Here is the result :
# **▶Video Explanation Of The Deployed Web App**
### Click On The Image to play the Video. : [](https://www.youtube.com/watch?v=8ZsUzq01A3w)
## **⚖️ Disclaimer**
**This is not financial advice! Use forecast data to inform your own investment research. No guarantee of trading performance.**