This notebook describes how to generate holdout predictions for a crypto perpetual funding strategy after its configuration has been selected using validation results. It resolves the highest-Sharpe eligible validation backtest, carries over the model…
Knowledge library
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.
Search the library
1,747 documents
This module defines a point-in-time simulation environment for executing a large sell order in crypto perpetual futures. Its observations combine remaining inventory and time with market volatility, premium index, relative volume, hour of day, and time to…
This document describes a pipeline for downloading official Binance USD-M perpetual funding records, normalizing them, and caching them in a columnar file. Monthly archives are fetched concurrently for the requested symbols and date range. The records are…
This analysis selects one configuration from a frozen pool of crypto perpetual-futures candidates spanning four prediction labels and multiple strategy stages. It chooses the highest validation Sharpe and treats label, split, and execution details as part of…
This notebook compares gradient boosting configurations for crypto perpetual futures using features built around the premium of perpetual contracts over spot. It varies tree capacity and loss function, including squared, absolute, and Huber losses, and…
This notebook develops model-based features for crypto perpetual futures: per-asset conditional volatility forecasts from GJR-GARCH and a market-wide stressed-regime probability from a two-state Gaussian hidden Markov model fitted to funding settlements.…
This case study lays out a research pipeline for crypto perpetual futures, treating funding payments exchanged between long and short positions at regular settlements as a potential return source. It describes data and model stages from label construction…
This strategy builds a grid for range-bound perpetual futures trading, with gold and other lower-volatility assets given as intended markets. It activates only after three range checks pass: a low regression slope, highs and lows that do not both move…
The strategy pairs a short perpetual futures position with a long spot position in the same cryptocurrency. The hedge is intended to reduce exposure to the coin’s price direction while collecting funding when the rate favors shorts. It proposes selecting…
This strategy searches across perpetual-futures venues for token pairs with differing funding rates. It normalizes each venue’s rate by its payment interval, annualizes the comparison to a daily horizon, and selects the most favorable long/short venue…
This workflow describes a bidirectional grid for cryptocurrency perpetual futures. From an initial reference price, it places long levels below and short levels above; positions are opened as price reaches grid steps and are intended to close when price…
This strategy uses changes in USDT supply as a proxy for liquidity conditions in Bitcoin markets. It proposes going long when supply reaches a new high over a rolling window, then closing the position or going short when supply falls to a new low. A…
This short-term futures approach monitors Binance liquidation data, filters small events, and compares recent liquidation volume with its historical average using a Z-score. A surge with a strongly one-sided liquidation mix creates a candidate signal. The…
This framework combines three components: a cash reserve floor, recurring purchases of a core asset, and a smaller alpha sleeve that trades selected crypto perpetual contracts. The reserve rule skips purchases when spending would breach the configured…
This long-only Bitcoin strategy uses a 14-period RSI on a four-hour timeframe to arm entries when RSI falls below 38. It adds up to five safety orders at fixed price declines from the base entry, with each order sized about 1.8 times larger than the previous…
This document describes a long-only dollar-cost averaging setup for an INTC-linked USDT perpetual futures market. It starts with a base order and adds equal-sized safety orders as price falls, using progressively wider price steps. The configuration…
This crypto futures strategy seeks to keep account value balanced between available stablecoin funds and a long position. It compares available balance with the leveraged value of the position. When either side exceeds a configurable threshold, it adjusts…
This workflow describes an automated crypto perpetual-futures system that combines short- and long-term EMA crossovers with news sentiment. It evaluates completed candles to identify golden or death crosses, then gathers recent RSS coverage and has an AI…
This document describes a market-making system for Binance USDC perpetual futures. Its numerical core analyzes recent trade flow and price profiles alongside estimated buy- and sell-side market impact. The signal combines directional flow, shifts in volume…
This strategy trades a basket of USDT-margined crypto perpetuals by comparing each asset’s price relative to Bitcoin with a basket index. It maintains a smoothed reference level for each coin-to-Bitcoin ratio, then uses deviations from the index to guide…
This 30-minute ETH perpetual strategy combines directional trend, RSI limits, relative volume, and two momentum measures to select long and short entries. It offers two ADX calculation variants. Long entries require positive directional movement, ADX above…
This note describes a moving-average crossover approach for following trends. It calculates a fast EMA and a slow EMA, using a 12-period and 26-period pair as examples. A fast EMA crossing above the slow EMA signals a long entry, while a downward cross is…
This strategy uses candle direction and body size to enter long or short positions. It compares the latest candle’s body with half of an exponentially smoothed body-size measure over the recent 30 bars. A sufficiently large bullish candle can trigger a long,…
This workflow has multiple language models act as virtual traders, each maintaining a separate simulated account and producing standardized position actions. Their decisions use technical readings from daily, hourly, and five-minute intervals, including RSI,…