📈 Recurrent Neural Networks for Stock Price Prediction 🚀

📜 Abstract

In this exciting project, we delve into the world of finance and technology by exploring the use of Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, for the dynamic task of predicting stock prices. 🌐 This repository is a treasure trove containing a detailed research paper and a practical Jupyter Notebook. Together, they demonstrate the power and intricacies of applying deep learning techniques to financial forecasting. 💹

🛠 Installation

To embark on this journey of financial data analysis with RNNs, ensure you have Python 3 installed. Then, gear up your machine learning toolkit with these packages:

pip install numpy pandas tensorflow keras keras_tuner scikit-learn matplotlib seaborn plotly yfinance statsmodels arch

📊 Usage

To dive into the analysis:

1. 🌟 Clone this repository to your local machine.
2. 📓 Open the Jupyter Notebook (Assignment 3- Variyas.ipynb) in your favorite Jupyter environment.
3. 🚀 Run the cells in sequence to witness the magic of data transformation, model building, training, and evaluation in action!

🔍 Methodology

Our adventure includes these pivotal steps:

• Data Acquisition 🌐: Fetching historical stock price data using the yfinance library.
• Data Preprocessing 🧹: Cleaning and normalizing the data for the RNN feast.
• Model Building 🏗: Crafting and tuning various RNN architectures, including the mighty LSTM and the agile GRU.
• Training and Validation 🏋️‍♀️: Training the models on historical data and validating their prowess.
• Evaluation 📈: Measuring the predictive accuracy with meticulous metrics and analyses.

📝 Research Paper

Accompanying this repository is a scholarly research paper (Assignment 3- DL- Variyas.pdf) that sails deep into the theoretical oceans of RNNs. 🌊 It encompasses a thorough literature review, an elaborate methodology, and a critical analysis of the results. This paper is a beacon guiding through the complexities and nuances of stock price prediction using deep learning. 📘

👨‍🔬 Credits

• Author: Variyas Nitin Singla 🎓
• Institution: The University of Adelaide 🏛
• Contact: Feel free to drop an email at a1872896@adelaide.edu.au for any queries or collaborations.

🙏 Acknowledgments

A heartfelt thanks 🌟 to the esteemed faculty and the vibrant peer group at The University of Adelaide for their invaluable insights, feedback, and support. This project wouldn't have been possible without the collaborative and inspiring environment they provided.