Omira Documentations
  • ๐ŸงชOmira Labs
    • Introduction
    • Predictive Intelligence In DeFi
  • Omira API
    • Introduction
    • Access Packages
    • Request Access
    • API Documentation
  • ๐Ÿ”ฎB.B4 Prediction Models
    • Introduction
    • Model Whitepaper
    • dL: The "Degen" Model
  • ๐Ÿค–0.07 Agent model
    • Introduction
    • Model Whitepaper
      • Model Personalization
      • Simulate Market Events
      • Trading Applications
  • ๐Ÿ“ˆThe SmartSwap DEX
    • Litepaper Overview
  • ๐Ÿช™The Omira Token
    • Introduction
    • $OMIRA Token
  • ๐Ÿ“–The Manual
    • Accessing B.B4
    • Accessing B.B4 dL
    • Tips & Tricks
  • โ›ฐ๏ธDevelopment Path
    • Omira Token: Utility & Value Expansion
    • Roadmaps
      • Phase 1: Development of B.B4
      • Phase 2: The Rollout and More
      • Phase 3: Development of 0.07 & More
      • Phase 4: The Expansion
  • ๐Ÿ“šResources
    • ๐Ÿ–ฅ๏ธOmira Labs Website
    • ๐Ÿค–B.B4 Model Web
    • ๐ŸฆX
    • ๐Ÿ“ฒTelegram Group
    • ๐Ÿช™Omira Token Web
    • Terms and Disclaimer
Powered by GitBook
On this page
  • Introducing B.B4-dL
  • Change in Confidence Threshold
  • Feature Engineering Adaptations
  • Differences in accuracy
  1. B.B4 Prediction Models

dL: The "Degen" Model

Our risk-on alteration of B.B4

Introducing B.B4-dL

B.B4-dL proposes a more risk-on version of the already-existing standard B.B4 model. Two main differences are in effect; a fine-tuned confidence threshold and an adapted feature-engineering process.

Change in Confidence Threshold

A fine-tuned confidence threshold allows B.B4-dL to deliver predictions even when its confidence is less than that of the base model. Rigorous back-testing and simulations allow for the generation of larger amplitude predictions to occur while still maintaining acceptable accuracy.

Feature Engineering Adaptations

Existing features within the B.B4 model have also been strategically adapted to allow for the creation of B.B4-dL. Tweaked parameters, adjusted feature weights, and modified algorithms associated with these features allow the model to maintain an enhanced sensitivity to larger price movements without comprising overall effectiveness.

The adapted features in B.B4-dL are designed to be more responsive to sudden market shifts, increased volatility, and significant trend changes. They are fine-tuned to capture the broader nuances and dynamics that are more like to precede or follow larger price swings. By incorporating these optimized features into B.B4-dLโ€™s overall training process, dL is much better equipped to identify price movements aligned with risk-tolerant traders.

Differences in accuracy

Its important to note that due to the fact that dL is better suited to identify larger price movements, B.B4-dLโ€™s accuracy is metrics differ from the base modelโ€™s. The directional accuracy of B.B4-dL remains almost identical to that of the base model, while the RMSE and MAPE are slightly raised due to the more volatile nature of its predictions. In simple terms, B.B4-dL maintains the same accuracy in predicting trends, with a slightly higher chance of over/under shooting the outcome price-action.

B.B4-dL builds upon the solid foundation of the standard B.B4 model while incorporating optimizations that enhance its performance for those seeking to capitalize on larger price movements.

PreviousModel WhitepaperNextIntroduction

Last updated 5 months ago

๐Ÿ”ฎ