This project presents a comprehensive analysis of Nestlé India's stock performance using Power BI for visualization and machine learning models for predictive insights. It covers historical trends, price movements, trade volumes, and volatility over time.
| Tool | Purpose |
|---|---|
| Power BI | Interactive data visualizations and dashboard design |
| Python (ML) | Applied basic machine learning models for forecasting |
| Jupyter Notebook | Used for data preprocessing and model training |
- 📆 Trend Charts: Year-wise trends for average price (WAP), turnover, and trades.
- 📉 Volatility Detection: Identifies volatility spikes (e.g., March 2020 – COVID impact).
- 🥧 Distribution Pie: Compares high, low, open, and close prices.
- 📊 Comparative Bar Charts: Shows yearly comparisons of high/low prices and trade volumes.
- Built predictive models to estimate future WAP (Weighted Average Price) and stock turnover.
- Evaluated models using regression metrics such as RMSE and R² score.
- Cleaned and prepared stock data using pandas, scikit-learn, and matplotlib.
This project combines visual analytics and predictive modeling to explore the financial performance of Nestlé over the years. It provides both business insights and technical exposure — ideal for students, analysts, and beginners in data science.
This project is for educational and non-commercial use only. The data used is sourced for learning purposes.