NASDAQ Data Analysis
Overview
Constructed time-series forecasting models using advanced statistical techniques to analyze NASDAQ, S&P 500, and CFTC market data. This project focuses on identifying cross-market correlations, predicting market dynamics, and deriving actionable financial insights.
Key Features
- Bayesian Modeling: Applied kernel-based regression to identify trends and correlations.
- Volatility Prediction: Leveraged Prophet for robust market forecasting.
- Data Exploration: Analyzed historical market trends across major indices for actionable insights.
- Technical Indicators: Integrated Bollinger Bands, RSI, and MACD for enhanced trend analysis.
Tools Used
- Programming Languages: Python
- Libraries/Frameworks: Orbit, Prophet, Plotly, Pandas, NumPy
Current Progress
- Data Integration: Successfully merged datasets from NASDAQ, S&P 500, and CFTC data sources. All files are aligned by date and cleaned for consistency.
- Technical Analysis Implementation:
- Calculated key indicators like Moving Averages, Bollinger Bands, RSI, and MACD for NASDAQ stocks.
- Visualized trends using dynamic and interactive charts to identify potential breakout signals.
- CFTC Correlation Study: Conducted initial analysis of trader positioning and its correlation with S&P 500 index movements.
- Error Handling & Debugging: Enhanced robustness by handling missing or inconsistent data files. Added checks for sufficient data length for rolling calculations.
Next Steps
- Forecasting Models: Develop and validate time-series forecasting models using Prophet and Orbit.
- Cross-Market Analysis: Explore deeper correlations between CFTC trader data and market movements to predict macroeconomic impacts.
- Actionable Insights: Automate the generation of buy/sell/hold signals based on combined technical indicators.
- Scalability: Implement scheduling for regular updates of data and automated analysis pipelines.