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.
5,018 documents
The post asks whether an AI system can infer a profitable futures trader’s approach from minute-level transaction records and then automate similar decisions. The trader reportedly combines minute-bar patterns with discretionary market feel, making the…
The Neural Weight Oscillator combines normalized trend, mean-reversion, and momentum readings into a bounded 0–100 indicator. It uses the Best-Worst Method to turn pairwise importance judgments into component weights, then optionally adjusts those weights…
This brief educational note defines quantitative investing as expressing an investment strategy in code so that a computer can carry out trading in place of manual execution. It identifies reduced emotional interference as one potential benefit of rule-based…
This document presents a Chinese-stock ranking workflow built around an XGBoost RankNet model. It constructs price-return and trading-activity features, labels stocks using clipped forward returns divided into quantile bins, and separates training data from…
This book section surveys advanced MQL5 capabilities for building MetaTrader 5 software. Topics include custom financial symbols, economic calendar events, networking, databases, cryptography, libraries, software packages, and organizing related programs…
This short troubleshooting note addresses a BigQuant model-training failure that reports a ValueError because a maximum is being computed over an empty sequence. It attributes the problem to a parsing issue when feature or factor names are renamed. The…
The report describes stock-return prediction with machine-learning models built for short, medium, and long forecast horizons. It groups selection factors according to their information coefficients at different horizons, reflecting the idea that factor…
This research summary outlines three refinements to genetic programming for finding stock-selection factors: fitness measures based on mutual information and long-only excess return, ways to transform nonlinear factors, and validation procedures intended to…
This commentary reviews the Chinese quantitative-investing environment in 2022 and presents a private manager’s expectations for 2023. It attributes a difficult path to excess returns to weak trading activity and rapid shifts in market style, alongside a…
This weekly report compares artificial intelligence stock-selection portfolios across broad A-share universes, industry-neutral portfolios, and portfolios restricted to the CSI 300 or CSI 500. It names XGBoost, support vector machines, random forests,…
The document introduces Markov chain Monte Carlo as a numerical approach for approximating Bayesian posterior distributions when analytical integration is impractical, especially in models with many parameters. It explains the Metropolis algorithm as a basic…
This code module outlines methods for constructing sparse portfolios intended to exhibit mean reversion. It includes Box–Tiao canonical decomposition, greedy support selection, semidefinite optimization under volatility constraints, and sparsity methods…
The document explains lookahead bias: a backtest can accidentally use future candle data because the full historical dataframe is loaded before indicators and signals are calculated. This can make results appear unrealistically strong. It describes an…
This Chinese-language report summary reviews the history and practice of machine learning in quantitative investing. It says that machine learning was used in the field during the early-1990s boom and that its applications continued in algorithmic trading…
This report overview describes the longstanding use of machine learning and artificial intelligence in quantitative investing. It notes that applications were already present during an early-1990s wave of interest, and that use continued in areas such as…
This roundtable transcript gathers views from Chinese investment managers, researchers, and futures professionals on the development of quantitative investing. Participants discuss the tension among scale, returns, and risk; the challenge of declining or…
This weekly report compares machine-learning stock-selection portfolios across several Chinese equity universes: broad-market stocks without industry neutralization, broad-market selections neutralized to the CSI 300 or CSI 500 industries, and selections…
This configuration defines a Qlib workflow for training a TabNet model on Alpha158 features for CSI 300 stocks, using Chinese market data and the CSI 300 index as benchmark. It sets a historical data window, separates fitting, validation, and test periods,…
The document describes a tool for checking whether a trader’s actions and recent outcomes are associated with subsequent losses. It trains a neural network on eight features from closed trades, then reports validation accuracy relative to a majority-class…
This note explains how to handle low-frequency financial or analyst factors alongside daily price and volume factors when constructing nonlinear models. One approach is to merge monthly or quarterly fundamentals with daily market data and carry the latest…
This brief note describes a feature-selection exercise based on a random forest template. The author says they ranked 37 stock factors by random forest importance and retained the nine factors with the highest importance scores. The document does not…
This Chinese-language research summary discusses forecasting stock-selection factor returns after commonly used factors became more volatile. It focuses on screening timing variables with Lasso and Elastic Net regression, then extending factor timing with…
The submission contrasts discretionary and quantitative investing. It describes quantitative work as gathering and cleaning high-dimensional data, calculating factors, and using rules to make trades programmatically. It also suggests that machine learning…
The article challenges three barriers often thought to exclude individual investors from quantitative trading: advanced mathematics, coding skills, and large capital. It presents quant methods primarily as statistical tools for understanding markets, and…