Articles and backtests tagged #Backtesting | FlashAlpha

Guides and insights

Guides, explainers and comparisons on options analytics: dealer positioning, volatility, flow and the FlashAlpha API, for traders and developers.

Looking for tested results? Studies are listed under Backtests.

43 articles and backtests tagged #Backtesting×

Machine Learning on Options Data: Quant ML Guide

Options data is one of the densest public-markets modalities and one of the worst-served by ML toolchains. This guide surveys eight ML methodologies that have published research or plausible workflows on options - production-proven (realized-vol regression, deep hedging), research-backed (sequence models on surfaces, anomaly detection, event studies), and speculative (regime classification labels, generative augmentation, GNNs) - the data shape each one needs, what is minute-level in history, and the tier and SDK package that lets you ship without rebuilding the pipeline.

Point-in-Time Options Greeks: How to Backtest Strategies Without Lookahead Bias

Point-in-time options Greeks are delta, gamma, theta, and vega exactly as they were computable at a past minute, using only data available then. Most options backtests reconstruct Greeks with hindsight and silently inherit lookahead bias. This is how to backtest with leak-free point-in-time Greeks via the FlashAlpha Historical API, with runnable Python and the pitfalls that quietly inflate Sharpe ratios.

I Backtested 96 SPY Put Credit Spread Strategies Over 7 Years - Here's What Actually Worked

Seven years of 1-minute SPY chains. 96 grid cells. Honest fills, signal-gated sizing, drawdown breaker. Same cell ran +5,400% with a stop loss and -100% without. Multi-DTE pooling somehow underperformed single-DTE. SL=200% turned out worse than no stop at all. The best signal in 16k trades was a one-line flag that beat my 3-layer composite. The Calmar-leader cell is in the grid - I'm telling you the shape, not the coordinates.

No articles match your search.


Showing 28 to 36 of 43 results

Tested results live in Backtests

Studies that test one trading question on historical data and report what happened, grouped by the plan that opens the full results.

Join the Community

Discord

Engage in real time conversations with us!

Twitter / X

Follow us for real-time updates and insights!

GitHub

Explore our open-source SDK, examples, and analytics resources!