This project aims to predict Roche stock prices using regression analysis on time series data and machine learning modeling. By gathering microeconomic and macroeconomic data from publicly available APIs and incorporating financial statements from company websites, the goal is to create accurate predictions for stock prices. In contrast to a fundamental analysis, this project is a deep dive into the mathematics and modeling behind the numbers.
Stock prediction is a challenging yet crucial task in financial markets. This project utilizes regression analysis and machine learning techniques to predict Roche's stock prices. By leveraging a combination of microeconomic, macroeconomic, and financial statement data, the aim is to build robust models capable of making accurate predictions.
- Integration of microeconomic and macroeconomic data
- Utilization of financial statements from company websites
- Time series analysis
- Machine learning modeling for predictive analysis
- Publicly available APIs for microeconomic and macroeconomic data
- Financial statements obtained from company websites
- Time series data from historical stock prices
- Regression analysis
- Machine learning algorithms (e.g., linear regression, random forest)
- Time series analysis
- Data preprocessing, visualization, and feature engineering
A recommendation is included at the end of the notebook that considers the results of the analysis. This is not professional financial advice, but simply my opinion included in a personal project.
To use the project:
- Clone the repository to your local machine.
- Install the required dependencies.
- Run the Jupyter Notebook to see the results. Alternatively, take a look at the results of running the code in this repository.