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.
32 documents
The document explains FreqAI’s main software components and how they support model development. A persistent model object handles data collection, feature engineering, training, and inference; a per-asset data kitchen provides processing tools and metadata;…
The document explains how FreqAI trains trading agents through reinforcement learning. An agent processes historical candles and chooses among actions such as entering or exiting long and short positions. A custom reward function scores its decisions, while…
The guide explains how to enable public trade downloads in Freqtrade and configure order flow processing. Settings control cached candles, trade history depth, footprint price-bin size, and the volume and ratio thresholds used to identify imbalances.…
This quick start explains how a Freqtrade strategy turns exchange candle data into indicators, entry and exit signals, and orders. A strategy is implemented as a Python class with separate methods for calculating indicators and populating long or short…
The document explains how to inspect backtest performance by entry and exit reasons in Freqtrade. It describes exporting signal data, then grouping trade outcomes by entry tag, exit tag, and pair. These views range from an overall summary to detailed pair…
This guide explains how to download and maintain historical market data for strategy backtesting and hyperparameter optimization. It covers choosing pairs, timeframes, exchanges, and date ranges; refreshing existing datasets incrementally; and adding earlier…
The document explains how Freqtrade’s Hyperopt process searches strategy parameter combinations by repeatedly backtesting historical data. It begins with random combinations and then uses an Optuna sampler to explore parameter spaces while minimizing a…
This documentation explains how to start Freqtrade and select the configuration, strategy, data directory, and database used by a bot run. It outlines command-line options for live or simulated trading, including dry-run balance and fee settings, and notes…