LogoLogo
  • Welcome to xFractal
  • Core Capabilities & Key Components
  • xFractal Technology
    • Scoring Engine
      • The Hype Score
      • The Trading Score
      • The Safety Score
    • xAS - xFractal's Agentic System
      • Autonomous Agents and Their Roles
      • Key Agent Components
      • Agents Actions
      • Intent Recognition
      • (Soon) Know Your Trader (KYT)
    • Aya
    • Oblivia - Price Predictions
  • xFractal Platform
    • dApp
      • Onboarding
      • xFractal Compute Credits (XCCs)
      • Natural Language Interface
        • Prompting guide
      • Predictive Insights
      • Hub (Referrals and Leadeboard)
        • Leaderboard
      • (Soon) Trading Terminal
      • (Soon) Explore
  • OTHER
    • Referrals
    • Partners
    • Pricing
    • Protocols Supported
    • Troubleshooting
    • FAQ
    • Privacy Policy
    • Terms of Use
    • Team Telegram Contacts
Powered by GitBook
LogoLogo

© xFractal 2025

On this page
  1. xFractal Platform
  2. dApp

Predictive Insights

PreviousPrompting guideNextHub (Referrals and Leadeboard)

Last updated 3 days ago

xFractal’s Predictions module helps forecast price movements by analyzing a blend of token-specific data, market signals and wallet behaviour. It powers key decision-making across the platform by offering high-confidence directional predictions.

Predictions are made for price in the next 24h. These can be unlocked by using XCCs. Predictions are updated on a daily basis at 15:10 CET.

How It Works

xFractal aggregates a variety of inputs including:

  • On-chain activity

  • Price trends & volatility

  • Social metrics

  • Technical indicators (e.g. MA, RSI)

These features are passed through multiple forest-based classifiers, each outputting a probability of upward price movement.

Model Ensamble

Rather than relying on a single model, xFractal combines outputs from multiple classifiers using a weighted ensemble approach. This improves overall reliability and helps smooth out noise from individual predictions.

Final Output

The ensemble produces a combined probability, which is compared against a dynamic threshold:

  • 1 = price likely to go up

  • 0 = price likely to go down or stay flat

Performance

The model achieves 82% direction accuracy across all predictions, with performance improving to 85% for high-confidence signals. Notably, price increase predictions are 83.6% accurate. Ensuring predictions are both accurate and actionable

Unlocking Predictions

Predictions can be unlocked for 1 XCC. Once unlocked, users can review the prediction output and instantly act on it by selecting Quick Buy.

Disclaimer: Not Financial Advice

All predictions and insights provided by xFractal’s machine learning models are for informational and educational purposes only. They do not constitute financial, investment, or trading advice. Past performance is not indicative of future results. Always conduct your own research and consult with a qualified financial advisor before making any trading decisions. Use xFractal's Predictive Inisghts at your own risk.