📈TREND PULSE

This repository implements LSTM is for the purpose of stock prediction​.

- Team Information:

- We are the students of Second Year E&CS Department.
- Group L-13
- Details have been linked below the image.

Devansh Shahane (Team Lead)

• Email ID: shahane.rhythm@gmail.com
• Linkedin ID: Devansh Shahane

Prathamesh Sharma

• Email ID: prathameshsharma27@gmail.com
• Linkedin ID: Prathamesh Sharma

Nirbhay Tiwari

• Email ID: nirbhay.tcet26@gmail.com
• Linkedin ID: Nirbhay Tiwari

Motto: " We Together Can Bring A Change "

📈 Trend Pulse

Predicting Stocks with ML

Trend Pulse 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: 📈TREND PULSE

- To Run it effectively, with more crisp understanding: Run On Google Colab

- A Easier Presentation, has been linked here: A Quickie

📊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. :

⚖️ Disclaimer

This is not financial advice! Use forecast data to inform your own investment research. No guarantee of trading performance.