Project Overview

Data collection and preprocessing from financial APIs.
Conducted Exploratory Data Analysis (EDA) to analyze market trends and identify patterns.
Implemented Recurrent Neural Networks (RNN) for stock market prediction.
Evaluated the RNN model using performance metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).
Visualized and analyzed predictions versus actual stock prices to assess model accuracy and performance.

Technologies Used

• Python
• Pandas
• NumPy
• machine learning
• deep learning
• Matplotlib

Key Features

• Data collection and preprocessing from financial APIs.
• Exploratory Data Analysis (EDA) to understand market trends.
• Implementation of various machine learning models like Linear Regression, Decision Trees, and LSTM neural networks.
• Model evaluation using metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).
• Visualization of predictions vs actual stock prices.

Results

The model achieved significant accuracy in predicting stock prices, demonstrating the potential of machine learning in financial forecasting.