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 report frames next-day direction in China’s Wind All A-share index as a binary classification task. It trains a decision-tree-based AdaBoost model on 51 daily features drawn from several markets and asset classes, including repo rates, credit spreads,…
This example introduces support vector machines through a hypothetical animal-classification task. It defines seven numeric features and labels an observation positive when every feature falls within a specified range. Randomly generated observations and…
This Backtrader example defines a signal strategy using a fast and a slow simple moving average, with configurable periods. A crossover drives long entries; an option enables long-short signals. The script loads historical data, sets starting cash and…
This event page outlines a presentation on moving from discovering individual factors to designing their portfolio weights. It identifies linear and nonlinear combinations and ICIR-based weighting as methods, with attention to their underlying rationale and…
This configuration defines a Qlib experiment using Alpha158 features for the CSI 300 and the Shanghai 300 index as benchmark. It normalizes features with robust z-scores, fills missing values, filters a selected subset of columns, and applies cross-sectional…
These release notes describe changes across versions of the VeighNa trading framework. For quantitative research, notable updates include a cross-sectional percentile ranking function, revised factor and signal performance analysis, an added VWAP matching…
This document describes a live AUDCAD strategy on hourly bars. It enters short after a bullish candle closes above the upper 20-period Bollinger Band, and enters long after three bearish candles coincide with a close below the lower band. The stated…
This guide explains how to obtain exchange history for OctoBot Script backtests and how to reuse previously downloaded data. The fetch request is configured with a trading pair and candle interval, with optional settings for the starting timestamp, exchange,…
The report describes applying OpenFE, an enumerate-and-filter framework, to discover interpretable fundamental factors from Chinese companies’ balance sheets, income statements, and cash-flow statements. It first removes fields with substantial missing data,…
This notebook demonstrates a workflow for running an online portfolio moving average reversion algorithm in Zipline and analyzing its output with pyfolio. The example applies OLMAR to a fixed basket of seven stocks, estimates relative mean deviations from a…
This research summary describes a monthly sector-rotation framework for Chinese equities. It groups 29 CITIC first-level industries into financial, cyclical, consumer, and growth sectors, builds market-cap-weighted sector indices, and proposes selecting…
This document is a QuantStats tear sheet comparing a strategy labeled “vwap-plain” with SPY over January 4–9, 2026. It reports a 0% total return for the strategy, a 0.12% maximum drawdown, a 0.76 Sharpe ratio, and 50% time in the market. The benchmark’s…
This post outlines a Chinese stock-selection screen combining a positive MACD reading, a signal described as prior-day institutional control, and alignment among several moving averages. It presents the original screen as requiring at least five averages to…
This note describes a timing strategy based on the rotation between large-cap and small-cap stocks in China’s A-share market. It compares the recent performance of the CSI 300 and CSI 500 indexes, representing the two size groups, and selects the stronger…
This indicator estimates the expected value of a long trade held for a fixed number of bars in two ways. Its empirical engine repeatedly samples overlapping historical trades, optionally applying take-profit and stop-loss rules, then calculates average…
The document proposes screening Chinese stocks for daily range above one percent, membership in the robotics concept group, circulating market capitalization below 10 billion yuan, and a rounded price pattern on the prior trading day. It presents example…
The document explains how a simulated trading engine processes each market-data point in three stages: the exchange matches existing orders against the updated market, strategies receive the data and can issue commands, and venues settle eligible commands…
The document describes a ProRealTime indicator that plots how often a chosen variable falls into a set of value bands over a recent sample of candles. The user selects the variable of interest, such as normalized price range or an indicator reading, then…
This reference introduces MyLanguage, a domain-specific language for writing programmatic trading analyses on the FMZ Quant platform. It explains scalar and sequence data, strings, numeric and Boolean values, global variables, naming conventions, and…
The document introduces Zhice, a strategy research workspace within VeighNa Fusion. It describes a staged workflow that takes a user's trading idea through clarification of the logic, code drafting and review, backtesting, parameter optimization, and results…
This forum post compares backtest results for a 20-day and 110-day moving-average strategy on Vanke A shares across two platforms. The strategy buys when the shorter average exceeds the longer one and exits when it falls below, using full portfolio…
This research summary describes an A-share market-impact model intended to narrow the gap between simulated strategy returns and realized portfolio returns. It argues that applying one fixed slippage rate cannot reflect how impact varies across stocks,…
This Chinese equity selection note outlines a screen for stocks in a designated metaverse industry group. Its initial description calls for simultaneous bullish crosses in three technical indicators and a previous-day auction turnover threshold. The more…
This strategy ranks country exchange-traded funds by estimated market beta, measured against a U.S. equity index using a rolling year of daily prices. Each month, it divides the available funds around the median beta, going long the lower-beta group and…