01 Multi-Agent Orchestration
Event-driven multi-agent coordination system for auction-based procurement, inventory allocation, and real-time fulfillment under demand uncertainty.
13 projects
Research, built
Simulations, interfaces and agentic systems built around the research questions — some from the work itself, some from hackathons, some from curiosity.
01 
02 RiskSentinel - Agentic Systemic Risk Simulator
Multi-agent systemic risk simulator for financial contagion analysis on 210 S&P 500 stocks, built for Microsoft AI Dev Days Hackathon 2026 and deployed as an interactive Streamlit app.
03 Island Model + MultiVeStA — Statistical Model Checking of Economic Growth
Accepted paper at MARS @ ETAPS 2026. Reproduces and extends Fagiolo & Dosi (2003) Island Model using MultiVeStA for statistical model checking, with formal convergence guarantees on parameter sensitivity analysis.
04 Robust Portfolio Optimization under Systematic Market Disruptions (PFSE)
Novel PFSE estimator achieves 25% breakdown point with 32× computational speedup over MCD. Out-of-sample Sharpe 1.87 on S&P 500 (2015–2025), 29% lower drawdown during COVID-19. Submitted to Computational Economics.
05 PokéNexus
Personal side project that merges my long-standing love for Pokémon with graph visualization, interactive systems, and Python prototyping.
06 Network Topology Analysis for Systemic Risk Prediction
Financial machine learning project combining dynamic correlation networks, graph neural networks, and trading backtests to detect systemic risk in U.S. equity markets.
07 NLP & Semantic Network Analysis
Technical implementation of the JADT paper pipeline, integrating multilingual preprocessing, topic modeling, correspondence analysis, semantic spaces, sentiment modules, and network-based validation across methods.
08 Advanced Recommender System
Learning-to-rank recommender system for next-best-action prediction, combining Bayesian optimization and ensemble ranking to improve NDCG@5 by 36%.
09 Real Estate AI Agent
Autonomous AI agent for property-market analysis, price estimation, and natural-language interaction built on predictive models and LLM orchestration.
10 Lightweight Fine-Tuning with PEFT & LoRA
Parameter-efficient fine-tuning pipeline using LoRA to adapt DistilBERT for sentiment analysis while training less than 1% of the model parameters.
11 Gas Network Risk Forecasting
Second-place hackathon project for gas leak risk prediction using geospatial-temporal features, synthetic data augmentation, and SHAP-based interpretability.
12 AI Photo Editor with SAM & SDXL
Computer vision and generative AI pipeline combining SAM and SDXL for interactive object segmentation and photorealistic image editing.
13 Custom Chatbot with RAG
Retrieval-augmented chatbot that combines semantic search, custom embeddings, and LLM prompting for grounded domain-specific conversations.