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 document reviews an empirical comparison of machine learning approaches for forecasting monthly returns in China’s A-share market. The described process trains models on prior data, uses a validation period for tuning, and tests predictions out of…
The document summarizes a study of machine learning models for predicting monthly Chinese A-share returns. It describes a rolling, annual retraining design that uses lagged stock and macroeconomic factors, with separate training, validation, and test…
This research summary reviews tests of eight proprietary price-volume factors in Chinese equities, comparing monthly, weekly, and biweekly rebalancing. The factors include active buying and selling, smart money, ideal amplitude, APM, ideal reversal, large-…
This example describes a daily, long-only futures strategy using a 10-period average crossing a 30-period average to generate entry and exit signals. A 120-period moving average acts as a trend filter: the strategy opens a position after an upward crossover…
The document outlines a workflow for building equity strategies that adapt their stock-selection logic to market conditions. It proposes measuring market sentiment with signals such as the number of limit-up stocks and average returns, then adding industry…
This post is a satirical warning about trusting impressive quantitative strategy claims and backtest curves. It points readers toward shared deep-learning strategy code, but supplies no description of the model, training data, signals, or validation process.…
This study examines how factor information decay can guide multi-factor stock selection. It defines a factor’s half-life from the time required for its information coefficient (IC), or IC information ratio (IC_IR), to fall to half its initial level. The…
The article describes slippage as the gap between an intended price and the actual fill, and attributes its size to both network delay and the speed of price movement. It argues that backtests and simulated trading can understate this effect because they do…
This document describes a configurable backtest strategy for several TheStrat price-action patterns. It classifies bars as inside, outside, two-up, or two-down, then tests selected continuation and reversal combinations, including 2-1-2, 3-1-2, 3-2-2, 1-2-2,…
The document outlines a MetaTrader 5 framework for backtesting event-driven strategies using historical economic calendar data. A retrieval script collects past events over a selected date range and saves country, event, and timestamped value data in files…
This example demonstrates how to run a local backtest with synthetic minute-level prices and a simple strategy. The strategy waits for its first trading iteration and then submits a buy order for one share of a demonstration stock. The backtest uses a small,…
This configuration describes a Qlib workflow for training a PyTorch feedforward neural network on China’s CSI 300 universe. It uses Alpha360 features, robust feature normalization, missing-value filling, and cross-sectional rank normalization of labels. The…
The article presents a robust version of equal risk contribution (risk parity) portfolio construction. It treats the estimated covariance matrix as uncertain and builds a bounded uncertainty set around the estimate. The optimization then accounts for…
This research note describes an enhancement strategy for China’s CSI 1000 small-cap equity index. It combines factors representing valuation, growth, trading behavior, capital flows, and network relationships within index constituents. After neutralizing for…
This article outlines the engineering challenges of researching and backtesting systematic options strategies. Because listed contracts change over time, a historical test needs an accurate record of which contracts were available on each date. The described…
This MetaTrader expert advisor follows a time-based routine using the Color3rdGenXMA moving average. At a specified hour and minute, it checks the indicator color and opens a short position for red or a long position for blue. It closes the position after a…
This research summary describes how to build and compare active and passive portfolios of Chinese healthcare-themed funds. For active funds, it argues that screening should use actual underlying holdings, since a fund's label may not reflect a concentrated…
This notebook outlines a daily equity research workflow using CSI 300 constituents. It loads historical bars, builds an Alpha158 feature dataset, and defines training, validation, and test periods. The target is a forward VWAP return over a three-day…
This document describes an Expert Advisor that trades signals from the Digital CCI Woodies indicator. A signal is generated when a bar closes and the indicator’s cloud changes color. The page also notes that the compiled indicator file must be installed in…
This Chinese-language README catalogs resources for systematic trading research and implementation, including backtesting frameworks, trading libraries, data sources, strategies, books, videos, blogs, and courses. Its listings span multiple asset classes and…
This note describes a Chinese equity screening rule that combines daily price range, a ranking based on net large-order volume, and a cap on circulating shares. It presents the combination as a way to find smaller stocks with active trading and short-term…
This proposed Chinese stock screen selects companies associated with the metaverse concept, with circulating shares at or below 5.5 billion, and a product shape described as rounded or arc-shaped. The post says the shape criterion is subjective and…
This overview distinguishes language generation from financial prediction, arguing that strong text generation does not by itself solve markets’ low signal-to-noise ratios, changing patterns, and limited data. It explains GPT’s development and instruction…
This documentation page catalogs Freqtrade features and settings that have been deprecated or removed, then explains migration implications for strategies and stored market data. It covers command-line options, pairlist configuration, strategy interfaces,…