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
This tutorial builds a PyTorch LSTM model to predict the next Bitcoin closing price from recent open, high, low, close, and volume data. It explains the model’s input and output dimensions, the role of sequence length and batch size, and how to connect a…
The document describes adapting a fixed-weight, multi-indicator trading strategy by feeding its combined indicator score into a small neural network. Indicator weights vary by classified market state, but are initially hand-set. The proposed model uses the…
This document presents a multi-stage approach to trading Polymarket event contracts. Rule-based filters first reduce the market universe using liquidity, trading activity, spread, competition, and implied-probability limits; for each event, the system…
This document outlines changes to an AI-driven cryptocurrency system intended to address delayed exits, lack of historical learning, one-sided trade selection, and repeated losses. Its main architectural change separates the slower strategy process, which…
This document describes a cryptocurrency rotation system that ranks liquid coins using a composite of moving-average arrangement, spread changes, and the direction of several averages. It selects high and low scoring assets for potential long and short…
The document describes a workflow that turns a natural-language trading hypothesis into code, retrieves cryptocurrency data, calculates factor diagnostics, and returns an interpreted report. Its stated checks include information coefficient, monotonicity,…
This article recommends using AI to study existing trading strategies instead of asking it to generate a complete system from a natural-language prompt. The proposed workflow is to select a strategy, ask AI to explain its overall logic and components, probe…
This tutorial builds a PyTorch LSTM to forecast the next Bitcoin closing price from hourly open, high, low, close, and volume data. It explains the LSTM input and output dimensions, sequence length, batch ordering, hidden and cell states, then shows…
This document describes an experiment integrating Jev’s structured judgments into a Binance USDT-margined perpetual strategy. The model receives order-book state, recent trades, short-term price changes, and volatility, while positions, order sizes, and…
This document describes a research framework for tracking how price moves may spread across companies linked by an AI theme. It builds a universe from equity contracts, excludes ETFs and indices, and uses a language model to assign companies to multiple…
This article recounts using ChatGPT alongside a quantitative trading platform to learn basic strategy coding and interpretation. Its concrete example asks the model to produce a Pine Script strategy that takes long positions when a short moving average is…
This account turns a market-comment observation about the KDJ indicator’s J line into a crypto trading strategy. The proposed signal combines the size and direction of recent price movement with the speed and direction of J-line changes: certain combinations…
The document describes APFF, a cross-sectional long-short strategy for USDT-margined perpetual contracts. It ranks a universe of contracts using five seed factor families: momentum, short-term reversal, funding rates, premium, and open interest. Raw signals…
This controlled study asks whether frequent model updates adapt to changing markets or absorb short-term noise. It compares four logistic regression variants in one Rust process: a fixed model, per-sample online updates, periodic rolling-window retraining,…
This tutorial describes training an agent to choose hold, buy, or sell actions for Bitcoin using a recurrent Proximal Policy Optimization model. It pairs an LSTM policy and value function with a custom Gym-style backtest environment. The environment supplies…
The article walks through an automated crypto perpetual-futures system that gathers account, market, and position data, sends a structured context to a large language model, and routes its output to an execution module. Its market inputs combine…
The article presents an automated workflow for discovering and refreshing cross-sectional factors for crypto perpetual contracts. It selects liquid markets, classifies volatility conditions, prompts an AI system to propose factors, and evaluates candidates…
This guide explains how to connect Claude Desktop to FMZ through the Model Context Protocol (MCP). It walks through obtaining FMZ MCP configuration credentials, adding the configuration to Claude Desktop, restarting the app, and authorizing tool access. The…
This document outlines an automated research and execution workflow for mining factors across liquid crypto perpetual contracts. At scheduled intervals, it selects markets by trading volume, classifies volatility conditions, reviews the health and coverage…
This overview compares six programming language categories for quantitative trading: visual programming, EasyLanguage-style tools, Python, Matlab and R, C++, and Java or C#. It evaluates them qualitatively on functional range, speed, extensibility, and…
The article proposes assigning trading tasks to tools suited to their uncertainty and computational cost. Deterministic checks, such as moving-average signals, position limits, and stop losses, are presented as fast and repeatable rules. Language models are…
This experimental strategy combines a short- and long-period EMA crossover with sentiment analysis of recent cryptocurrency news. It collects RSS items from multiple sources, filters and orders them by recency, and sends the technical signal, news, and…
The document presents a workflow for using an AI coding assistant alongside a local strategy project and FMZ. The local project stores source code, configuration exports, design notes, tests, and reports; remote synchronization updates platform source, while…
This tutorial builds a Bitcoin trading environment for reinforcement learning, using historical OHLCV data, a rolling observation window, and actions that buy, sell, or hold at varying position sizes. It describes random data slices for training, serial…