behavioral-modeling

A complete machine-learning system that predicts AI assistant user satisfaction using behavioral signals such as device, usage category, time features, session metrics, and model metadata. Includes full ML pipeline, SHAP explainability, evaluation suite, and an interactive Streamlit analytics dashboard.

Interaction-centric behavioral modeling for earnings calls using multimodal neural fusion, text-audio divergence, and Q&A interaction dynamics.

Household decision simulation through persona-enriched multi-agent negotiation. The HDSim method core.

Residential mobility and relocation decision simulation via persona-enriched multi-agent negotiation (PEMAND)

Household travel decision simulation via persona-enriched multi-agent negotiation (PEMAND)

Autonomous AI agent with dynamic mood-state engine, persistent user memory via entity extraction, and behavioral pacing - deployed with Docker + PM2

A sophisticated Python framework for modeling and simulating psychological personality systems. This project enables dynamic personality evolution through event simulation, allowing for realistic modeling of how life experiences shape personality traits and psychological attributes.

Conceptual research architecture for adversarial behavioral modeling — defensive security framing, unvalidated by design, and self-audited in an epistemic autopsy. Research/theory document, not operational tooling.

Комплексная система для генерации реалистичных траекторий перемещения людей в городской среде. Проект сочетает паттерны проектирования, пространственный анализ с OSMnx и статистическую валидацию против реальных данных

AI-powered social media simulation framework using LLMs for modeling Twitter dynamics during crisis events. Built for SBP-BRiMS 2024 Twitter Challenge.

Longitudinal player-state modeling of disengagement and recovery in PowerWash Simulator gameplay telemetry.

Developed an integrated consumer analytics framework combining Conjoint Analysis, Structural Equation Modeling (SEM), K-Means Clustering, and Logistic Regression to understand discount preferences, segment consumers, and predict purchase behavior in the apparel industry.

Learns from your own browsing, entirely on your device — nothing is ever transmitted. Ships descriptive: the one model that beat its baseline on 1,326 people is switched off, because a data gate set in advance was not met.

Python project analyzing behavioral baselines, deviations, and social role dynamics in ethological data using analytical frameworks inspired by cybersecurity anomaly detection.

Agentic LLM system for behavioral user modeling and personalized recommendation — DSN x BCT Hackathon 3.0 submission.

Agentic Behavior Observatory - paste a GitHub repo URL and get a live, evidence-linked analysis of how it models agentic behavior: agent-based simulation, synthetic populations, LLM-based behavioral modeling, reinforcement learning and evaluation rigor, plus the demographic dimensions and model versions it rests on.

Customer upgrade behavior intelligent dashboard using ABM, persona modeling, churn-risk analysis, long-term upgrade readiness scoring, and CRM action routing.