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 documentation explains design choices behind TqSdk, a Python trading software development kit. It aims to avoid imposing a strategy model: users can fetch data and issue orders freely, while examples demonstrate possible applications instead of…
This trend-following expert advisor uses the slope of a simple moving average, expressed as an angle, to distinguish directional markets from flat conditions. It also measures price distance from the average as a percentage to avoid entries after a move has…
The report describes an asset allocation approach that measures cycle states and uses machine learning to estimate the probability that assets will outperform one another. It reviews macroeconomic timing frameworks, then describes cycle factors derived from…
This configuration specifies a Qlib workflow for training the HIST model on Alpha360 features for CSI 300 stocks and evaluating its signals in a portfolio backtest. The data handler normalizes features, fills missing feature values, drops rows without…
This forum question concerns adding a moving-average exit condition to an AI stock-selection backtest. The proposed logic waits until a minimum holding period has passed, then examines positions in reverse StockRanker prediction order and sells eligible…
This reference describes the fields used by FMZ trading data structures, including market trades, tickers, candlestick records, orders, and conditional-order configurations. It covers identifiers, timestamps, prices, quantities, volume, open interest, order…
This Expert Advisor contains two Vortex Indicator trading systems, one for long trades and one for short trades. Each side has its own settings, including a distinct magic number and position-sizing method, and can be enabled or disabled independently. The…
This document describes an Expert Advisor that trades signals from a volume-weighted moving-average indicator. It enters when a bar closes with a newly colored signal, following a bar with the opposite color or no color. The approach therefore uses a change…
The document presents a trend-following indicator similar in purpose to Supertrend, but its trailing reversal level is set using a fixed percentage-like step from the close rather than a multiple of average true range. The level adjusts with the direction…
The document presents a way to estimate how often a one-minute Chinese convertible-bond bar closes above its open after three consecutive up bars. It converts each bar’s return into a binary up-or-not indicator, scans the series for three up bars, and counts…
This review of factor performance during the 2018–2020 quant crisis examines why diversified equity strategies struggled. It analyzes standard size, value, investment, profitability, and momentum factors, alongside portfolios formed by sorting stocks on size…
This report presents a three-layer fundamental quant framework: macro indicators and scenario analysis, sector-level earnings and valuation measures, and portfolio strategies. Its macro view combines growth, monetary and credit conditions, and inventory…
OsMaSter is an expert advisor that opens positions with a fixed volume and uses specified stop-loss and take-profit levels. The document lists its basic settings, including position volume and an identifier for the EA, but does not explain the entry or exit…
This post proposes screening equities for turnover within a specified range, seven consecutive down days, and a rising-bottom price pattern. It frames the combination as a way to examine stocks after a decline while looking for a possible base or rebound.…
This post describes a stock screen that combines at least five overlapping moving averages, a share price below a stated ceiling, and revenue growth between two fiscal years. The intended rationale is to find stocks with clustered trend measures and a…
This Chinese-language post proposes an equity screen using three conditions: amplitude above a threshold, rising price lows, and positive returns. The rationale is to exclude stocks with little movement, identify a potential base with progressively higher…
The post proposes a Chinese equity screen using turnover between 3% and 12%, a positive return over ten days below 35%, and a dividend payout ratio above 25% for 2019. It says to select stocks before 10 a.m. and presents the dividend filter as a way to…
The article outlines how Amberdata datasets can be accessed through Snowflake, Google Analytics Hub, and Databricks. It frames these integrations as a way for institutional researchers and traders to work with historical and fresh digital-asset data using…
This article describes a backtesting indicator for evaluating exit distances on a supplied trading signal. It simulates a single-unit position, closes equal portions at up to three take-profit levels, and exits the remaining position at the first stop level…
The forum exchange addresses whether a backtest for Shanghai Futures Exchange instruments needs to distinguish between closing a position opened the same day and closing one opened earlier. The question comes from a trader analyzing fill prices in a trade…
This Chinese-language post outlines a proposed screen for mainland Chinese exchange-listed stocks in the metaverse industry. It selects names among the five highest by the day’s auction trading value, then requires the weekly five-period moving average to…
This report presents a short backtest of a large-cap stock strategy attributed to a multi-agent AI trading bot and compares it with SPY. The stated test ran from January 4 to January 15, 2026, using Yahoo data and a universe of large technology and other…
The document describes a daily stock screen based on three conditions: a high-to-low range greater than one percent, a reversal or engulfing-style pattern, and a close above the previous day’s low. It presents these conditions as a way to find stocks whose…
This document describes a function for producing directional signals from the OsMA indicator: one return value represents a buy and another represents a sell. It says the function can be included in an expert advisor and called to check the current signal.…