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 tutorial introduces visual strategy construction through examples involving price changes, volume expansion, gaps, moving averages, MACD, and KDJ. Its main worked strategy applies threshold rebalancing between cash and Bitcoin: compare the market value…
The article introduces XGBoost as a boosting ensemble and contrasts its sequential fitting of weak learners with the parallel training used in bagging. It explains residual-based improvement, complexity penalties, sample and feature subsampling, and…
This developer guide explains two practical tasks for working with OctoBot strategies. Backtesting data collected through the regular collector is stored in SQLite files, which can be opened in a database browser to inspect historical candle records supplied…
This report summary outlines a method for inferring informed trading from minute-level data. It first applies a “smartness” measure to identify trades attributed to smart money, then aggregates their relative execution prices into sentiment factor Q. Higher…
This short assignment response describes quantitative investing as using data to check market observations and identify patterns. It frames the goal as building strategies that can be backtested and evaluated for stability over time, then using software to…
The document outlines a Chinese equity screening rule combining three conditions: RSI below 65, the current high at the highest level over two days, and the gain at 9:25 below 6%. It then adds a circulating market-cap threshold above 100 billion yuan. The…
This research note proposes that stock price changes reflect market forces, firm-specific short-term information, longer-term fundamentals, and noise. It uses daily minute data and cross-lag regressions of returns on changes in trading volume to estimate…
This article describes a Chinese equity screening approach that combines intraday price range, a large-order net-volume ranking, and the stock’s price change at the 9:25 opening auction. The intended screen seeks volatile, actively traded stocks whose early…
The post reports a backtest failure caused by subtracting a time-zone-naive datetime from a time-zone-aware datetime while checking whether orders have timed out. The strategy had loaded historical bars and begun replay, but halted when its timeout check…
The post outlines a low-frequency model for timing Chinese A-share exposure and selecting trading targets. It describes using daily Wind data and a large set of predetermined spreadsheet formulas to generate bullish or bearish signals and identify an…
This document describes an Expert Advisor that trades from signals produced by the NRTR indicator. A signal is recognized at a bar’s close when the indicator displays a large colored dot. The text does not specify the direction mapping, position sizing, or…
This article explains the claimed tendency for Chinese A-share markets to weaken on Thursdays through three proposed mechanisms: investors selling ahead of weekend cash needs under T+1 trading and restricted weekend transfers, investors reducing exposure to…
The document outlines an Expert Advisor that opens and closes positions at configured clock times. At the opening time, it uses the FigurelliSeries histogram relative to zero to select a direction: values above zero trigger a short, while values below zero…
The document presents a market randomness measure based on Shannon entropy as a filter for automated strategies. It describes estimating the distribution of log returns over a rolling window, then calculating entropy from the probabilities of discrete return…
This indicator seeks to identify quiet price ranges that may precede larger moves. It combines Keltner channel boundaries based on average true range with a standard deviation measure, then marks an upside or downside breakout when price crosses the relevant…
The article describes replacing the general-purpose MQL tick structure with smaller representations tailored to instrument type. For Forex and CFDs, a compact structure stores bid, ask, millisecond time, and flags; an exchange-oriented version also retains…
The document outlines a Bill Williams style trading method built from Alligator lines and five-bar fractals. It describes the Alligator as several smoothed averages of the high-low midpoint, with the slow line used as a reference. A fractal marks a local…
This brief BigQuant support exchange addresses a question about a backtest whose logs and apparent trade signals stop before the requested end date. The user says the run was set through the 23rd, exchange data stopped at the 17th, and the output log stopped…
This forum post raises a practical backtesting question: whether strategy data indexed by the current date can be used to trade at that same day’s open without introducing lookahead bias. The example ranks stocks using market capitalization, tradable market…
This post proposes a Chinese equity screen that combines moving-average alignment with recent limit-up moves. Its initial criteria are at least five moving averages meeting together and a limit-up within the prior 25 days. The post interprets these…
This Chinese-language post describes a stock screen focused on companies classified in the metaverse theme. It selects candidates using the previous day's actual turnover rate, bounded between 3% and 28%, and a price-amplitude threshold above 1. The…
This Chinese community post proposes a daily A-share screen based on recent net buying, prior-day trading value, and company size. The stated idea is to find smaller companies with positive buying activity and sufficient liquidity, while also describing the…
This Japanese-language README curates resources for systematic trading research and implementation, including backtesting and live-trading frameworks, analytics tools, data sources, books, papers, blogs, and courses. Its practical framing is to reproduce…
The article reviews empirical research comparing commodity futures momentum based on total returns with momentum based on residual, or idiosyncratic, returns after accounting for selected systematic factors. The study forms ranked portfolios across…