Stock Price Prediction / 30_Days_of_Python

[Bharat00007]

### Title: Issue with Stock Price Prediction Model

Description:

I am encountering issues with the stock price prediction model implemented in the Jupyter Notebook. The model aims to predict future stock prices using historical data. Below is an overview of the functionalities and the specific issue I’m facing.

Project Overview:

The stock price prediction project is designed to forecast future stock prices based on historical closing price data. The project utilizes a Bidirectional Long Short-Term Memory (LSTM) network, which is a type of recurrent neural network well-suited for time series data.

The key functionalities of the project include:

Data Loading and Preparation:

• Data Reading: Loads stock price data from a CSV file named google_dataset.csv.
• Feature Extraction: Extracts and normalizes the closing price of the stock.
• Data Transformation: Converts the time series data into sequences of 100 days to be used as input for the LSTM model.

Model Definition:

• Network Architecture: Defines a Bidirectional LSTM model with two LSTM layers and two Dense layers.
• Compilation: Compiles the model using the Adam optimizer and Mean Squared Error (MSE) loss function.

Training and Evaluation:

• Training: Trains the model using 70% of the dataset.
• Evaluation: Evaluates the model’s performance on the remaining 30% of the dataset.

Prediction and Visualization:

• Prediction: Generates predictions for the test dataset.
• Visualization: Plots the predicted stock prices against the actual prices.

Model Saving:

• Saving: Saves the trained model to a file named model.h5

[github-actions[bot]]

Thank you for creating this issue! 🎉

We'll look into it as soon as possible. In the meantime, please make sure to provide all the necessary details and context. If you have any questions or additional information, feel free to add them here. Your contributions are highly appreciated! 😊

You can also check our [CONTRIBUTING.md] for guidelines on contributing to this Domain.

[Walayhs]

Go ahead!