# dL: The "Degen" Model

### 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-dL’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-dL’s accuracy is metrics differ from the base model’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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://omira-documentations.gitbook.io/omira-documentations/b.b4-prediction-models/dl-the-degen-model.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.