Identify statistically significant trading signals with quantitative models across crypto and traditional markets.
npx skills add https://github.com/cubexch/ai-fund --skill jim-simons
Please help me install this Agent Skill. Skill: jim-simons Source: https://github.com/cubexch/ai-fund/tree/main/skills/jim-simons Command: npx skills add https://github.com/cubexch/ai-fund --skill jim-simons
Enable users to discuss and implement Jim Simons-inspired, pure quantitative trading with a robust statistical edge, free of emotion.
Backtest a mean-reversion signal across crypto pairs and review its edge, decay, and optimal Kelly-based position size.
High-intent search queries and answers about installing and using this skill.
To backtest a mean-reversion signal, you apply quantitative models to historical crypto pair data, validating statistical significance while analyzing edge dynamics, signal decay, and optimal Kelly-based position sizing.
Statistical arbitrage uses data-driven quantitative models to identify mean-reversion and cross-asset pricing inefficiencies. The framework validates signals statistically, ensuring tradable edges exist before applying risk-controlled sizing across markets.
Yes, you can apply Kelly criterion position sizing in traditional markets. The framework provides risk-controlled sizing guidance for signals across both crypto and traditional assets, incorporating transaction-cost-aware execution to optimize allocations.
Monitoring signal decay involves continuous tracking of edge dynamics after execution. The framework implements decay analysis to evaluate when quantitative signals lose statistical significance, enabling adjustments to data-driven risk management and position sizing.
Yes, transaction-cost-aware execution works for cross-asset arbitrage. The framework explicitly incorporates execution costs into signal validation and position sizing, ensuring statistical arbitrage edges remain profitable after fees across crypto and traditional markets.
OpenSuckerApply machine learning models to OHLCV data for market prediction and signal generation.
ccfCompute VaR, CVaR, drawdown, and risk-adjusted returns from pandas return series.
brainbytes-devImplement diversified cross-asset systematic investment strategies with risk budgeting and backtesting.
kayzaaRun quantitative trading algorithms and backtest strategies on historical market data using Python.
