ANPS-TradeMeUp is an LLM-powered AI News Prediction System for short-to-medium term market forecasting, featuring real-time analysis and a Dash-based monitoring dashboard.

Simple Finance Forecasting Ai. This Ai Model uses historical price data to forecast future prices. The model is trained on data downloaded from Yahoo Finance using the yfinance library, and predictions are made using a linear regression Ai model from sklearn. The model supports all the symbols supported by Yahoo Finance.

An end-to-end Python implementation of Cao et al.'s (2025) HLPPL methodology for the identification of financial (asset price) bubbles. Implements 7-parameter Log-Periodic Power Law model fitting, confidence-weighted sentiment analysis, regime-dependent 'BubbleScore' fusion, and Transformer-based forecasting with a backtesting framework.

Microservices-based AI trading architecture integrating multi-source data scraping, Transformer-based price prediction, and an autonomous Deep Reinforcement Learning trader, deployed under centralized supervision.

AI-driven Polymarket trading bot designed to analyze prediction market data and execute semi-automated trades using OpenAI and Claude models. The system evaluates market sentiment, probabilities, and trading signals to assist with intelligent decision making in prediction markets.

Ubiquant Market Prediction

Market Analysis and Prediction

👁️ 天眼 — Multi-agent population simulation for China market forecasting. 10K+ virtual consumers.

Python application that integrates multiple APIs and an external AI prediction system to analyze stock trends and provide investment recommendations (buy, sell, or hold) for the upcoming period.

An AI-powered forecasting system that predicts economic and market trends using multi-source financial, macroeconomic, and behavioral indicators.

Machine learning process to predict financial instrument prices up to 3 days

Hull Tactical v7.1: A regime-aware "grey box" strategy for S&P 500 prediction. Combines Econophysics (Chaos/Entropy) with LightGBM and "Smart Noise" logic to challenge the EMH. (Mean Adj. Sharpe: 0.806)

Polymarket automated forecaster for Bitcoin 5-min markets. Hands-off prediction system with continuous retraining, risk controls, and transparent on-chain result tracking.

Multi agent-based LLM pipeline for market analysis

Analyze and forecast natural gas prices using time series data, with seasonality decomposition and signal detection for trading strategy insights.

Predict where news-driven crowd biases will misprice a market, then fade them: GDELT news -> swarm of cognitive-bias LLM agents -> behavioral signal scores.

Polymarket quantitative signals for BTC 5-minute trading. Statistical analysis framework producing high-confidence directional predictions. Backtested with 87.3% win rate.

Automated BTC market signals for Polymarket traders. Real-time directional predictions generated from multi-timeframe momentum and volume analysis. Python bot with CLI interface.

Project analyzing the relationship between El Niño weather patterns and cocoa futures market volatility using NASA satellite data and financial market analysis.