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.
5,018 documents
The article describes a beginner’s use of a trading platform and ChatGPT to learn strategy scripting, inspect example strategies, and run backtests. It includes an AI-generated moving-average crossover example with stop-loss exits, then illustrates asking…
This tutorial outlines a data-mining approach to machine-learning signals, contrasting it with strategies that begin from an explicit market inefficiency such as trend following or mean reversion. It recommends defining the prediction target and evaluation…
This article discusses how to structure instructions for AI-assisted crypto trading. It argues that prompts should provide current market inputs, account constraints, trading history, and a required output format, then describes a two-layer setup separating…
This article outlines an automated workflow for turning a written trading hypothesis into a preliminary factor test. A user submits an idea through messaging; an AI model translates it into JavaScript, the workflow retrieves cryptocurrency data, checks data…
This article describes two simulated workflows connecting AI-Trader, a cloud agent runtime, and FMZ. In one direction, an agent reads a live FMZ strategy’s output through MCP and publishes a corresponding signal to the signal platform. In the other, it…
This article demonstrates how to use ChatGPT inside FMZ’s strategy editor to help design, explain, and refine trading code. Its worked example combines one-minute bars into longer minute-based bars by grouping records into time intervals and aggregating…
This platform guide describes a visual, node-based workflow for connecting market data, external information, analysis, decision logic, and trade execution. It outlines node categories for AI analysis and agents, data transformation, flow control, custom…
This article describes a quantitative prediction workflow that turns each recent candlestick window into a tabular sample for TabFM, a foundation model for tabular data. Each row contains OHLCV values from completed bars, arranged as lagged fields, and the…
The document describes a prototype that turns crypto traders’ stated methods into a computable consensus process. It first converts BTC daily market data and macro inputs into structured states, including trend, momentum, volatility, recent price ranges,…
The article presents a single-instrument trading system that cycles through market perception, decision, execution, trade review, and playbook updates. It structures technical indicators covering trend, momentum, volatility, and volume, and combines that…
The document explains why a profitable historical backtest may fail in live markets, especially when a strategy is tuned and judged on the same limited sample. It recommends splitting chronological price history into an earlier training segment for parameter…
The article outlines an automated workflow for trading tokenized US stock contracts through a crypto platform. A scheduled process gathers account positions, news sentiment, and daily stock candles; calculates MACD, RSI, ATR, and OBV; asks a language model…
The article introduces Bayesian statistics through its historical development, from De Moivre’s forward probability questions to Thomas Bayes, Richard Price, and Laplace’s work on inverse probability. The central idea is to infer an unknown parameter from…
The article presents a two-part workflow for newly listed crypto perpetual contracts. A slower analysis process detects exchange announcements, tracks candidate tokens, and gathers basic token metrics, news, and derivatives data such as prices, funding…
This article describes a workflow intended to interrupt impulsive crypto trades by requiring a trader to state a reason before acting. It combines the trade idea with position information, news-based sentiment, and technical indicators such as MACD, RSI,…
This strategy screens USDT perpetual contracts for strong 24-hour gainers, then collects open interest, funding rates, market capitalization, and daily candles. Hard filters remove crowded shorts, low open interest, and coins that have already pulled back.…
This proof of concept runs four AI models in parallel on the same market data. Each model makes independent decisions using multiple timeframes and technical indicators, then trades in a virtual account. The system ranks models by realized profit and copies…
The article describes integrating Jev, a model that returns choices, scores, or probabilities, into a Binance USDT-margined perpetual strategy. It feeds the model order-book data, recent trades, short-term price changes, and volatility, while local code…
This article builds a Bitcoin trading agent with a recurrent neural network and Proximal Policy Optimization. The policy selects among holding, buying, or selling, while a custom backtest environment returns rewards based on changes in account value relative…
This essay proposes assigning deterministic trading tasks to explicit rules and reserving AI for decisions that require interpretation of unstructured information. Moving-average signals, position limits, and stop-losses are presented as rule-based tasks,…
This tutorial proposes pairing a rule-based bidirectional grid with an AI-assisted workflow. The grid handles routine entries and exits, while workflow nodes monitor market data and positions, check trigger and cooldown conditions, gather sentiment…
This article outlines a system that turns an analyst’s posts on X into potential trades in US equity perpetual futures. It proposes collecting posts through an RSS feed, asking a language model to identify explicitly named tickers and classify direction and…
This tutorial outlines an automated workflow for trading crypto-settled contracts that track U.S. stocks. It combines account position data, news sentiment, and daily stock prices, then uses an AI model to interpret short- and longer-term signals. A workflow…
The article recommends using AI to study existing strategy code instead of relying on it to generate a complete trading system from a loosely specified idea. Its learning process is to select an existing strategy, ask for an explanation of its structure and…