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.
16,761 documents
This multiday strategy trades the FTSE 100 as an IG Markets CFD on hourly bars. It uses QQE signals crossing the midpoint for entries, with a Universal indicator as a directional filter. Month-specific multipliers adjust long and short position sizes,…
This research summary examines whether excluding stocks ranked poorly by high-frequency factors can improve a Shanghai-Shenzhen 300 index-enhancement portfolio. It compares three construction methods: combine standardized factors into one score, use a…
This guide explains how Zipline data bundles package pricing history, corporate-action adjustments, and asset metadata for backtesting. It covers listing available bundles, ingesting a data source, choosing a specific ingestion by timestamp, and cleaning up…
This overview presents LumiBot as a Python framework for writing conventional rule-based strategies, AI-agent strategies, or combinations of the two. Its workflow supports running historical backtests before connecting to a broker, then running a strategy in…
This document describes an Expert Advisor that trades signals from the XWPR_Histogram_Vol indicator. It enters when a bar closes after crossing an overbought or oversold level. The two levels correspond to separate positions, each with its own magic number…
The document presents a Chinese equities screening rule using turnover, circulating share count, circulating market value, and the early-session price move. Its stated final criteria require turnover no greater than 12%, circulating market value above 100…
The document describes a simple momentum test on constituents of China’s Growth Enterprise Market index. It buys a stock at the next day’s open after a limit-up day, with parameters that can be changed to study different indices and holding periods. The…
The document describes a reporting workflow for analyzing a trading strategy from return data and, when available, holdings, transactions, benchmark returns, market data, and factor information. Its full report brings together return and event analysis, then…
The article discusses translating plain-language trading rules into Python strategies for the QMT platform. Its example is a moving-average crossover on a named Chinese equity, with an all-in position rule and adjusted price data. The author reports that an…
The document describes using genetic programming to discover stock-selection factors from intraday price and volume data. Factor expressions are represented as trees; successive candidate populations are produced through selection, crossover, and mutation.…
This Freqtrade strategy generates long entries when both the Commodity Channel Index and Relative Strength Index fall below configurable thresholds. It exits when both indicators rise above separate exit thresholds. Indicator periods and thresholds are…
This document outlines a stock screen that combines MACD above its zero line, upward-dispersing moving averages, and seven consecutive declining sessions. It interprets positive MACD and rising averages as technical trend conditions, while the sequence of…
This document describes a stock selection screen that combines RSI below 65, a rising 30-day moving average, and a condition described as today’s increase in position share exceeding 5%. The accompanying explanation presents the moving average as a trend…
The document outlines an end-to-end portfolio construction framework that embeds a differentiable convex optimization layer within a neural network. Raw asset data passes through the network for feature extraction and combination, then an optimization layer…
The document explains how to connect Databento historical market data to Lumibot backtests. It covers API-key setup, asset definitions, timeframes, date-range configuration, caching, and handling common retrieval errors. Examples include stocks, continuous…
This Expert Advisor takes trades from signals generated by the MACD-2 indicator. A signal is evaluated when a bar closes. Depending on the selected trend mode, entry can follow a histogram crossing of the zero line, a change in histogram direction, or a…
This guide outlines six compact trading bot demos, each built around a single AI agent using plain-language instructions and built-in data tools. The examples include discretionary stock selection, market news, news sentiment, trend following, a…
This Expert Advisor trades from the KalmanFilterCandle indicator. It generates a signal when a bar closes and the indicator changes candle color, using that change as the trade trigger. The document refers to chart examples and a test for USDJPY on the…
The document describes an experiment for comparing randomized trade sequences, focusing on whether the direction of the first position affects the outcomes. It contrasts alternating sequences that begin with a buy and those that begin with a sell, with the…
This Qlib documentation explains how to simulate model-driven trading through a persistent account. A configuration specifies a model, a portfolio strategy, and initial cash; the system then generates orders from predictions, executes them under exchange…
The article examines whether minute-level net purchases by northbound investors through Stock Connect can help time Chinese equity index futures. It compares signals built from daily data with signals built from minute data, using CSI 300 and CSI 500…
This Expert Advisor uses the BlauHLM oscillator to determine when to enter trades. Its described entry conditions are a change in histogram direction, a break through the zero line, or a change in the signal-line cloud’s color. An input setting selects the…
This article outlines how to move a developed and backtested option strategy into live or simulated trading with VeighNa’s OptionStrategy module. It distinguishes access requirements for futures options and ETF options, including differences in simulated…
This Freqtrade strategy combines MACD direction with the Commodity Channel Index (CCI) to generate long entries and exits. It enters when MACD is above its signal line and CCI is at or below a tunable buy threshold; it exits when MACD is below its signal…