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 brief assignment reflects on translating discretionary investment ideas into a quantitative process. The author cites assessing future demand for a company’s product, with examples involving a stablecoin business in the context of US Treasury pressures…
This Chinese-language tutorial describes implementing a stock-ranking strategy in BigTrader by passing StockRanker predictions directly to the trading engine and coding the trade logic there. It allocates purchases among the top-ranked stocks using weights…
This study mines short-horizon price and volume factors for Chinese equities, then examines how transaction costs and rebalance frequency affect portfolio results. It uses genetic programming to generate candidate daily factors from conventional price and…
The author describes paying to rent several crypto trading strategies and losing money on most of them. A platform strategy reportedly made money earlier, while a more recent funding rate approach stopped working as futures and spot prices converged. These…
The document outlines an Expert Advisor that trades signals from the BrakeMA semaphore indicator. A signal is generated at bar close when the indicator reverses color and a large dot appears. This gives a basic rule for identifying a possible trend change,…
This Chinese-language FAQ compiles practical guidance for building and operating strategies on FMZ. It covers exchange API behavior, order and position handling, market and limit orders, contract sizing, rate limits, timestamp synchronization, and common…
The document describes an MT5 reporting script that groups account history by magic number and currency, with optional date filters and CSV export. It outlines measures including profit after swaps and commissions, win rate, time-weighted return, profit…
This description presents an Expert Advisor that uses a Digital MACD indicator to generate trade signals at bar close. Depending on the selected entry mode, a signal can involve the histogram crossing zero, a change in the histogram’s or signal line’s…
This post reports a data-quality question about one-minute BNB/USDT candles retrieved through a trading platform’s GetRecords interface. The author compares a candle for a specified minute in August 2018 with Binance’s displayed data. Open, high, low, and…
The document describes a hybrid trading system in which a neural network is trained to handle conditions that a basic trading system (BTS) does not address well. Its example assumes the base system follows trends, while neural network components identify…
This article proposes comparing a model's information coefficient (IC) and mean IC across training and test samples to assess predictive stability. It defines IC as the correlation between a model score and subsequent returns, using a five-day return…
This article outlines a monthly A-share stock selection example built from gross margin, return on equity, and a cash-flow-per-share to earnings-per-share measure. It notes that financial statements update infrequently and that related accounting variables…
This Expert Advisor uses the Blau Ergodic MDI oscillator to generate trade decisions. The described entry alternatives respond to a change in histogram direction, a move through the zero line, or a color change in the signal-line cloud. A mode parameter…
This document outlines an Expert Advisor that uses an XMA_Ishimoku_Channel indicator to generate signals. A signal is formed when a bar closes with price inside the channel boundaries. The text gives a historical test example for GBPJPY on the four-hour…
The article frames a quantitative model as a system that turns an investment idea into a testable and executable process. It divides that system into strategy, risk, transaction cost, portfolio construction, and execution models. Strategy research may be…
This module generates synthetic pairs whose relationship is defined by a hedge ratio and a mean-reverting cointegration error. It first simulates the change in one asset’s price as an autoregressive process, cumulatively sums those changes into a price…
This document describes a chart scanner that labels several price-action features: liquidity sweeps, structure breaks, fair value gaps, reversal patterns, and inside bars. It presents the scanner as a way to review multiple candle patterns directly on a…
This stock-screening proposal selects candidates before each trading day using three conditions: MACD above zero, positive trailing earnings multiple, and a positive large-order net-volume measure. The article interprets the MACD condition as evidence of an…
The document describes a daily macro trading process built around distinct research perspectives. Separate agents assess economic growth, inflation and interest rates, and debt, liquidity, currency, and central bank policy. A disagreement agent challenges…
The document explains how an automated trading system handles spot, margin, and futures modes. Spot trading uses unleveraged long positions, while margin borrows capital and futures trade derivative contracts that may incur funding payments. It distinguishes…
The document proposes a daily equity screen combining price range, company size, profitability, and trading activity. It selects stocks with a daily high-low range above one percent, market capitalization below 10 billion yuan, positive net income in each of…
This documentation page explains that a completed strategy execution can produce a report and gives the instruction used to generate it at the end of a run. A display option can open the report automatically in a browser. The page illustrates a report…
This document describes an indicator that lets users choose among a broad set of moving-average and smoothing methods, including simple, exponential, weighted, regression-based, volume-weighted, and filter-style variants. It also lists price series that can…
This document describes a China A-share stock selection and portfolio strategy ranked primarily by dividend yield. It filters out suspended and risk-flagged stocks, applies market-cap, positive and relatively low price-to-earnings, and share-price…