Welcome to the project! This project involves exploring stock market data for technology giants (Apple, Amazon, Google, Microsoft). We'll use yfinance to gather stock information and visualize it using Seaborn and Matplotlib. The focus is on analyzing stock risk based on past performance and predicting future prices using an Long Short Term Memory (LSTM) network.
Weekly assignments would be pushed to this repository. You are required to make a fork of this repo and push your notebooks(assignment solutions) to the respective folders within this repo.
During Week 1, we will review Python programming and explore Numpy and Pandas.
During Week 2, we will learn about matplotlib and seaborn which are python libraries used for data visualization.
Please code side by side on your notebooks parallely while going through the tutorials. You can use Google Colab, Jupyter Notebook.
In this week, we will learn basic financial terms like Moving Average, Daily Returns and correlation between different stocks.
- Moving Average
- Daily Return of a Stock
- How to Calculate Stock Correlation Coefficient
- How to create a stock correlation matrix in python
For those who prefer videos
- Covariance and Correlation Matrix of stock returns with Python
- Please refer the research paper to get idea of upcoming weeks content
In this week, we'll read up on RNNs and LSTM which will help us predict the future stock prices.
These will cover much of the theory you need to understand for LSTM, but we encourage you to look up how LSTM is implemented in code using scikit-learn.
The final assignment will be released soon.