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
The document presents a way to assess trading-system drawdowns across three dimensions: depth, time spent below a prior equity peak, and frequency of episodes. It describes a report generated from closed trading history, including current underwater status…
This research summary compares ordinary cross-validation with time-series cross-validation for model tuning on sequential data. Randomly assigning observations to folds can train a model on future observations and validate it on the past, violating the…
This competition update reports diagnostics for the ten highest-ranked anonymous factors and tracks a CSI 1000 enhancement portfolio. Factor profiles include average Barra style exposures and sector-level average Rank ICs, calculated from cross-sectional…
This Chinese A-share stock screen combines a daily range filter, a morning-star-style price pattern, and three moving-average crossover conditions. The formula reference requires the 5-day average to cross above the 10-day average, the 10-day above the…
This Backtrader example compares three ways to attach protective exits to a moving-average crossover entry: a stop set after the entry completes, a stop submitted alongside the entry using cheat-on-close behavior, and a parent-child order arrangement that…
This example generates order-latency records for a crypto trading backtest from historical feed data. It first keeps events that contain both exchange and local timestamps, then aggregates to one record per second using the last timestamps in each interval.…
This indicator studies monthly seasonality using separate in-sample and out-of-sample periods on monthly charts. For each calendar month, it calculates average open-to-close return and the share of observations that rose or fell. It then ranks average…
This document presents three moving averages that use only closing prices whose bar opening times fall within a configured daily time range. The simple version averages a specified number of qualifying observations. The exponential version applies the…
The document describes parameters for an automated trading program built around CCI(100) signal levels. A global signal threshold determines when a position opens, while a separate reverse threshold signals a position reversal. Other inputs cover stop-loss…
This study examines buying newly listed A-share stocks after they first break out of their initial trading limit-up sequence. It observes that some stocks continue to rise after opening, while their pullback, rebound, and trend patterns vary by stock and…
This Expert Advisor combines three independent systems that use ColorXPWMA_Digit indicators. Each system signals a potential trend change when a bar closes and its indicator changes color. The systems can be enabled or disabled separately, allowing their…
This document describes an Expert Advisor that uses the CronexAO oscillator. It generates a trading signal when a bar closes and the indicator’s cloud changes color. The description also notes that the compiled indicator must be installed in the platform’s…
This design document sets out policies for building a trading system around data integrity, controlled failure, and verifiable behavior. It prioritizes reliability, then performance, modularity, testability, maintainability, and deployability. Invalid…
This reference guide describes Lumibot as a Python framework for creating, executing, and backtesting trading strategies across several asset classes and broker or data services. It outlines the strategy lifecycle, including initialization and a recurring…
This post describes a daily stock screen for Chinese equities using three conditions: price amplitude above a threshold, daily MACD above zero, and a dividend measure for 2019 above a stated proportion of price. It says candidates are selected before the…
The report describes an expanded Black-Litterman asset allocation model that combines subjective views with quantitative portfolio construction. It uses behavioral finance and historical trend information, including momentum and reversal effects, to form…
This tutorial demonstrates replaying Bybit’s depth-500 order book deltas in a NautilusTrader backtest. It loads a daily archive or a small sample, converts the records into instrument-specific order book events, writes them to a Parquet catalog, and…
This example tests whether market capitalization is associated with next-day stock returns using repeated cross-sectional ordinary least squares regressions. It joins Chinese stock factor data to daily bars, calculates forward returns from the next close,…
This research summary examines the validity of mainland China Stock Connect ownership data and describes portfolio strategies built from investor holdings, sector allocations, style exposures, leading trades, and net capital flows. It reports persistent…
The document describes an Expert Advisor that trades signals from an XDPO histogram. A signal is generated when a bar closes and the histogram changes direction. The system relies on a compiled indicator file, and the text notes that a supporting…
This article surveys ten cryptocurrency trading bot platforms and outlines the kinds of automation they offer. Features described include grid trading within a price range, dollar-cost averaging, signal-based trading, market making, technical-indicator…
This trading system uses the JFatl_Digit_System indicator to generate signals when a bar closes with a colored state that differs from the previous bar, including a transition from an uncolored state. An Expert Advisor acts on those indicator transitions.…
This study builds a monthly Chinese equity factor from stock returns and volatility around intraday volume surges. It defines a surge as a minute when the increase in trading volume exceeds that stock’s daily average increase by more than one standard…
The document describes an equity screening idea combining daily price range, the opening price relative to a ten-day moving average, and a concentration measure. It presents the range threshold as a way to find volatile shares and treats an opening price…