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.
29,558 documents
This description outlines an always-in-market reversal trend-following system implemented as an MT4 Expert Advisor. It holds either a long or short position: a close above the highest price of the prior 100 days triggers a long entry and closes a short,…
The document describes a Chinese equity screen for stocks with amplitude above 1, a circulating share count no greater than 5.5 billion, and seven consecutive down sessions. It frames the high amplitude as a sign of trading activity, the smaller float as a…
The document describes using historical volatility patterns to guide trading and risk decisions in BTC and ETH derivatives. It discusses a volatility cone, which displays realized volatility distributions across time horizons, and realized volatility grouped…
This article describes a portfolio component for an event-driven backtester. A portfolio receives signal events, produces order events, and updates positions and holdings from fill events. The NaivePortfolio example tracks each symbol’s quantity, cash,…
The document explains how FinRL models automated stock trading as a Markov decision process. An agent observes market prices and features, acts in a simulated environment, receives rewards, and adjusts its policy to pursue higher cumulative reward. The…
This document describes an MQL5 class that acts as a pre-trade execution gate for Expert Advisors. It reads the terminal’s latest server ping and combines that figure with a wall-clock execution delay recorded around a trade operation. If the combined…
This document explains a graphical workflow for researching CTA strategies with historical data. It covers downloading market data, configuring a backtest with instrument details and trading costs, and reviewing equity, drawdown, daily profit and loss, and…
This proposed A-share screen combines amplitude above 1, a rising price base, and net inflow from large orders in the afternoon. The article frames the flow condition as a way to include stocks with apparent buying support, and suggests adding fundamental…
Millenium is described as a system that opens at most one trade per day, using a fast and slow moving-average crossover alongside a price-position filter. For a buy setup, the fast average crosses above the slow average and the current price is above both;…
This document describes a rules-based intraday strategy that takes short positions in the DAX on 15-minute bars. Entry requires the MACD to cross below zero while its signal line is negative, price to be below a long-period exponential moving average, and…
This note describes a Chinese equity screen for robot-concept stocks with a float market value below 10 billion yuan, turnover between 3% and 12%, and a three-session limit-up streak. It frames the streak as a way to find recently active stocks and orders…
This short forum exchange addresses how to model a monthly rollover strategy that trades futures and options together. The question is how to configure the backtest engine when the two instrument types have different transaction fees, especially when closing…
This code manages backtest outputs for momentum experiments. It reads results from multiple train and test intervals, aggregates captured returns, and can rescale those returns to a target volatility. It calculates performance summaries that include return,…
This stock-selection post combines three market filters: price amplitude above a threshold, a session high equal to the highest high over two days, and turnover within a specified range. It presents the range and high conditions as signals of recent price…
This post outlines a Chinese stock screener using price movement, trading activity, and share price. Its stated filters look for stocks with an amplitude above a threshold, current volume above a stated level, a high opening price, and a share price below a…
This example describes a daily portfolio rebalancer for five exchange-traded funds spanning US equities, long-term Treasury bonds, and gold. It starts by checking each holding’s weight against a target allocation. A rebalance is triggered on the first…
This short note presents a reusable wrapper for retrying exchange API calls that fail because of network problems. Rather than adding retry logic separately around account, order-book, or candle-data requests, the wrapper repeatedly invokes a supplied method…
This document describes an automated strategy that enters when price breaks the high or low of a prior candle on a selected timeframe, from one minute through one month. The user can set an offset from that candle’s extreme and optionally apply…
The document proposes a short-term Chinese equity screen requiring turnover between 3% and 12%, floating market capitalization between 5 billion and 10 billion yuan, and a KDJ K value below 20. The author interprets the low K value as an oversold condition…
The article introduces altcoins and decentralized finance as possible sources of diversification and excess returns. It describes an altcoin-season indicator based on the share of leading altcoins outperforming Bitcoin over a specified period, with a 75%…
This collection of trading anecdotes describes manual, high-frequency intraday futures scalping based on order-book changes, quick reactions, and repeated attempts to capture small price differences. Practitioners emphasize watching volume and position…
The report compares sparse covariance estimation, which sets selected off-diagonal elements to zero, with rotation-invariant methods that adjust sample covariance eigenvalues. The latter include simulation-based, linear, and random-matrix-based nonlinear…
This article surveys Microsoft Research’s published work on AI for quantitative investing, especially Chinese equity selection. It explains methods that use graph neural networks to represent relationships among stocks, attention mechanisms to adapt to…
This post proposes a stock screen combining a reported increase in daily position accumulation above five percent with an external-to-internal trading-volume ratio above 1.3. It also references 2021 as a time filter, describing it as a way to exclude…