Ripple（涟漪） 是一个基于 复杂自适应系统（Complex Adaptive System, CAS）理论 构建的 Agent-Native 通用人类社会行为预测引擎。 / Ripple is an Agent-Native universal human social behavior prediction engine built on Complex Adaptive System (CAS) theory.

Predictive Exam Analytics & AI-Powered Study Plan Builder. Ingests past exam papers, analyzes topic patterns, predicts upcoming topics, and generates personalized study plans.

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.

A forecasting utility that helps developers generate and visualize predictions from historical data, ideal for analytics or planning workflows.

Yang.skills · 全能内容创作运营超级Skills包

Prediction engine that can try and understand the employment pattern for a given employee and give some interesting insights

Offline multi-agent simulation and prediction engine by Ethan Cho 조여준, part of VentureOracle forecasting experiments

A full-stack artificial intelligence application predicting property prices in Pune using React, FastAPI, and XGBoost.

A multi-sport statistical rating & match prediction engine — Elo, Glicko-2, Bivariate Poisson, and Plackett-Luce models with a C++ core, Java/Spring Boot API, and Next.js frontend.

Psychohistory Prediction Engine — 138-year cycle analysis, structural pressure scoring, and falsifiable predictions for 2026-2040

Skill-graded paragliding flyability prediction engine for launch sites in Antioquia, Colombia. Phoenix LiveView + Oban + multi-source weather aggregation.

Explainable, self-calibrating football match-prediction engine (World Cup 2026): EV-optimal picks from de-vigged odds, self-grading backtests, 62 tests.

Prediction interface experiment by Ethan Cho 조여준 for VentureOracle-style AI and market signal tracking

Murmura: open-source AGPL prediction workbench for knowledge graphs, multi-agent simulation, and explainable scenario forecasts

Test trading strategies against historical market data using a desktop engine for Windows. Supports technical indicators like RSI, MACD, and custom algorithms.

Self-hosted fork of MiroFish that replaces Zep Cloud with Neo4j — fully offline multi-agent AI prediction engine with Docker Compose

Swarm Intelligence That Predicts Anything. HIVE deploys autonomous AI agents to research, debate, and forecast any scenario — delivering intelligence briefs with probability scores, risk analysis, and actionable strategy.

Federated collaborative document layout online classification and value prediction engine.

Hard hat detection using ML.NET and TensorFlow with ResNet V2 50 transfer learning. Trains in under 3 minutes with bottleneck caching.