Projects

• Estimated instantaneous volatility of cryptocurrency by combining a Heston-lite SDE with Kalman and Particle Filter; absolute log returns used as ground truth. Kalman R² ≈ 0.9998, Particle Filter R² ≈ 0.48–0.67, GARCH R² ≈ 0.09–0.17. Both filters outperform traditional GARCH models.
• Estimated smoothed volatility of cryptocurrency by combining a mean-reverting SDE with Kalman and Particle Filter; 100-period rolling std used as ground truth. Kalman R² ≈ 0.996–0.997, Particle Filter R² ≈ 0.995–0.999, GARCH R² ≈ 0.33–0.63. Both methods outperform GARCH for smoothed volatility tracking.

Developed a modular pipeline to identify and backtest predictive signals from crypto spot data. Achieved ~52% hit rate and Sharpe ratio > 1 using ensemble models and adaptive trading strategies.

Built a BERT-based sarcasm classifier with Hugging Face and TweetEval for real-time inference, demonstrating advanced natural language processing capabilities.

• Developed an automated file organization system using AI-driven content-based classification, improving file management efficiency by 40%.
• Calculated document similarity using two approaches: TF-IDF vectorization with cosine similarity, and semantic embeddings from spaCy’s en_core_web_md model.
• Integrated real-time file monitoring with Watchdog to automatically organize files into user-defined folders, reducing manual sorting time by 60%.

• Implemented Bayesian inference methods (MLE, MAP, posterior mean) for robust parameter estimation in probabilistic models.
• Optimized inventory with the Newsvendor Problem, reducing losses by 49.08% vs heuristic methods.
• Developed and deployed multiple classification models, including KNN, Logistic Regression, and Single feature models, to predict healthcare readmissions, achieving AUCs of 0.68, 0.80, and 0.78, respectively.
• Achieved up to 7.8% cost savings through predictive model optimization, improving decision-making in healthcare resource allocation.

Developed strategy bots for Yut, a traditional Korean board game competition. Tested minimax tree search and heuristic-based strategies. Final approach used heuristic evaluation with Bayesian optimization (Gaussian Process + UCB) for weight tuning. Consistently outperforms baseline strategy with 54-56% win rate.