Jane Street: Market Prediction EDA by Symbol
Data Science Finance Kaggle EDA
This analysis explores the Jane Street Market Prediction dataset, focusing on analyzing properties and patterns structured by individual stock symbols.
Key Insights
- Symbol-level Heterogeneity: Different stock symbols exhibit vastly different feature distributions and return profiles.
- Feature Correlations: Multicollinearity is highly prevalent among features within the same group, indicating potential for dimensionality reduction.
- Temporal Shifts: Data distribution shifts over time, which presents a significant challenge for model generalization.
Check out the complete code, visualizations, and modeling setup in the Kaggle notebook.
Kaggle Notebook
Explore the Full Analysis
Access the complete Kaggle notebook to view all source code, interactive visualizations, and model configurations.