Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
1,747 documents
This script description outlines a long-only grid for NOT/USDT perpetual futures. It places price levels between fixed upper and lower bounds, with either geometric or arithmetic spacing. The stated design buys as price crosses grid levels downward and sells…
This XBT futures strategy builds a sentiment score from price location and range across ten lookback windows spanning 1 to 89 bars. For each window, it compares the close with a range centered on an average price, scales that position by the window's price…
This single-instrument framework combines technical indicators, relevant news, current positions, and stored trading rules to produce structured AI decisions. Its workflow records market snapshots, applies position and confidence limits, manages entries and…
The document presents a Bitcoin perpetual futures strategy intended for one-hour charts, combining signals across daily, four-hour, and hourly timeframes. Its stated entry framework uses a daily EMA trend filter, four-hour RSI, and hourly RSI, MACD,…
This short-only strategy for XAUTUSDT perpetuals uses a three-minute RSI signal to start trades when RSI crosses down through an overbought threshold. It adds up to three averaging orders at progressively higher prices above the initial entry, with uniform…
This long-only averaging strategy for POL perpetuals arms an entry when the 4-hour RSI falls below a configured oversold threshold. After a base order, it places five additional orders at fixed percentage declines from the base entry, with order sizes…
This document presents a long-only averaging strategy for the INJ perpetual market. It arms an entry when the four-hour RSI falls below its configured oversold threshold, then places up to five additional buy orders at fixed percentage declines from the base…
This cryptocurrency perpetual-futures strategy offers three ways to set support and resistance boundaries: prior-bar highs and lows, Bollinger-style bands around the mean close, or an ATR-based channel. It evaluates only completed candles and excludes the…
This strategy trades the price difference between Bitcoin perpetual and quarterly futures on a one-minute cycle. It treats the perpetual price minus the quarterly price as a spread and assumes the spread tends to return toward a long-term level. The document…
This long-only SOL perpetual futures strategy arms an entry when 4-hour RSI(14) falls below 33. After the base order, it places up to five averaging orders at fixed price declines of 2%, 5%, 9.5%, 16%, and 25% from the base entry, with order sizes scaling by…
This proposed system uses a large language model to generate and revise candidate price-and-volume factors for a cross-sectional long-short portfolio of USDT perpetual contracts. It screens liquid instruments, classifies market conditions using Bitcoin…
This article argues that traders should begin with a workable strategy and build technology in response to problems encountered in live trading. Elaborate systems designed before trading can consume time without generating market feedback, and the imagined…
This article demonstrates a convex optimisation workflow for a crypto perpetual futures portfolio. It combines expected returns estimated from cross-sectional momentum and carry features with a breakout signal, then uses a covariance estimate to represent…
This article brainstorms possible inputs for a crypto statistical arbitrage model. It covers relative price moves between similar assets, short and long horizon trends, crowded spreads that may unwind with momentum, lead-lag effects across markets, and…
The article advises new trading businesses to begin trading with available skills and tools, then build operational capabilities in response to real market experience. It argues that constructing a large technology stack before trading can waste effort…
This article argues that traders should not make statistical significance the sole test for acting on an idea. In markets with short histories, rare events, or structural changes, a useful edge may not have enough observations to produce a reliable p-value…
This article demonstrates a practical way to reduce trading costs in a crypto statistical-arbitrage portfolio: keep existing positions until they drift sufficiently far from their target weights. The example uses perpetual futures, excludes stablecoins, and…
The article presents a workflow for studying and combining signals on Binance crypto perpetual futures. It examines carry from funding rates and cross-sectional momentum alongside a breakout measure based on closeness to recent highs. The author first…
The article explains how to express trading signals as expected returns, giving a common scale for comparing features and combining them with risk estimates and trading costs. Its example uses Binance perpetual futures and considers carry, short-term…
The article discusses two proposed crypto trading signals. The retail-flow factor uses order-book data to distinguish retail from institutional activity and treats unusually strong retail participation as a contrarian signal. The author reports a near-linear…
This notebook describes an out-of-sample backtest for a selected crypto perpetual funding strategy. It reuses predictions generated from training history that ends before the holdout period, then applies the chosen strategy configuration, including its…
This notebook rehearses a deployment cycle for a crypto funding-rate direction model. It trains a LightGBM classifier on historical Binance-derived perpetual data, fetches live hourly bars and funding rates from OKX, computes the model's features, and…
This notebook studies how ridge, lasso, and elastic net behave when a crypto perpetuals feature matrix measures one economic quantity—the premium—many different ways. Premium levels, changes, volatility, standardized positions, ranks, and related funding…
This document describes data access and alignment conventions for crypto perpetual futures and related on-chain series. It explains that premium-index bars are timestamped at their opening time: an eight-hour bar records the premium leading into the funding…