skills.rest
ruvnet
ruvnetCOMMUNITY
Explore all skills by this author →
Website𝕏@ruvGitHub

trader-train

Train LSTM, Transformer, and N-BEATS neural models on market data with confidence intervals.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#model training#confidence intervals#transformer#lstm#stock prediction#neural-trader#n-beats
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill trader-train
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trader-train
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-neural-trader/skills/trader-train
Command: npx skills add https://github.com/ruvnet/claude-flow --skill trader-train

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires neural-trader.

What problem does it solve?

Training and comparing neural prediction models for market forecasting requires manual setup of ML pipelines, model selection, and result tracking. This Skill automates training LSTM, Transformer, and N-BEATS models on ticker data and persists results for later analysis.

Core Features & Use Cases

  • Multi-Model Training: Train LSTM, Transformer, or N-BEATS models on any ticker symbol via the neural-trader CLI with configurable confidence levels.
  • Prediction with Confidence Intervals: Generate forecasts with horizons (e.g., 5 days) and 0.95 confidence intervals.
  • Model Comparison: Benchmark model types side by side to identify the best performer for a given symbol.
  • Result Persistence: Store training outcomes in the trading-analysis memory namespace and train SONA on model outcomes.
  • Use Case: A quant analyst wants to forecast AAPL prices. They train all three model types, compare validation metrics, and store the winning model's results for downstream trading decisions.

Quick Start

Train an LSTM model on the AAPL ticker with a 0.95 confidence interval and generate a 5-day prediction.

Frequently Asked Questions about trader-train

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I train an LSTM model on stock market data?▼

Run npx neural-trader with the --model lstm flag and a --symbol ticker such as AAPL, optionally adding --confidence 0.95. The Skill first verifies neural-trader is installed, then executes training and reports loss curves and validation metrics.

LSTM vs Transformer vs N-BEATS for stock price prediction?▼

The Skill supports all three architectures and includes a model-compare mode that benchmarks them on the same ticker. Run npx neural-trader --model-compare with a comma-separated model list to see which performs best for your symbol.

How do I generate stock predictions with confidence intervals?▼

Use the --predict flag with --horizon such as 5d after training, for example npx neural-trader --model lstm --symbol TICKER --predict --horizon 5d. Predictions include the confidence interval configured during training.

Does neural-trader need to be installed before training?▼

Yes, the Skill checks for neural-trader with npm ls and installs it via npm install --ignore-scripts neural-trader if missing. No manual setup is required beyond having npm available.

Where are neural trading model results stored?▼

Training results are stored in the trading-analysis memory namespace via the ruflo memory_store MCP tool, keyed by model, ticker, and date. SONA is also trained on model outcomes using the neural_train tool with the trading-model pattern type.

Related Skills

Explore More Finance & Accounting Skills→
DaddyElonMusk69DaddyElonMusk69

ccxt

Fetch unified public cryptocurrency market data from 100+ exchanges.

Community
Intermediate
andrew-starosciakandrew-starosciak
2

signal-validation

Validate trading signals with Wilson CI and binomial tests in Rust.

Community
Advanced
BankrBotBankrBot
80

Bankr Agent - Market Research

Retrieve token market data and technical indicators across multiple blockchains.

Official
Intermediate
ActiveInferenceInstituteActiveInferenceInstitute
13

geo-infer-time

Analyze time-dependent patterns in geospatial data with ARIMA and exponential smoothing.

Community
Intermediate