PulseAugur
EN
LIVE 23:46:58

27B LLM trained to generate profitable trading formulas

By PulseAugur Editorial · [1 sources] ·

A research paper details the development of a 27 billion parameter model, Qwen3.8-27B, trained using Multi-Reward Reinforcement Learning to generate one-line trading formulas. These formulas are then converted into daily trading portfolios on US stocks, evaluated across 12 reward channels. The system demonstrated improved performance, with formulas moving from a mean score of -1.37 to +1.80 and an equal-weight book returning +16.2% with low market beta over a year of unseen data. AI

IMPACT Demonstrates LLMs' potential in specialized financial applications, pushing the boundaries of reinforcement learning for complex pattern generation.

RANK_REASON The item describes a research paper detailing the training and results of a large language model for a specific application (trading formulas). [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

27B LLM trained to generate profitable trading formulas

How we ranked this

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a research paper detailing the training and results of a large language model for a specific application (trading formulas). [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Aleksei Romanov ·

    Teaching a 27B Model to Write Trading Alphas: 101 Formulas, 12 Rewards and One Unseen Year

    <p>Qwen3.8-27B is trained with multi-reward RL to write one-line trading formulas in the language of WorldQuant’s <a href="https://arxiv.org/abs/1601.00991" rel="noopener noreferrer">101 Formulaic Alphas</a>. A deterministic verifier turns each formula into a daily dollar-neutral…

RELATED ENTITIES

RELATED TOPICS