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
This article explains why a strategy that performs smoothly on historical data can fail in live trading. It distinguishes rule discovery from quantitative implementation: researchers may mine historical market data to invent or combine rules, then add and…
This study applies TabNet, a neural network architecture for tabular data, to A-share stock selection. It outlines TabNet's encoder structure, in which attentive masks select features at successive steps, and explains the motivation for combining neural…
This example describes a daily AI-driven process for selecting sector ETFs. Five agents cover technology and communications, financials, healthcare, energy, and consumer sectors, each proposing an idea. A risk manager reviews the pitches for crowded…
This strategy combines model-based stock ranking with trend timing to seek medium-term growth opportunities in a manually selected China Securities 150 universe. The author frames it as a blend of valuation-oriented selection and signal trading: an AI model…
The document gives a broad introduction to quantitative trading as the use of data, statistical or machine-learning models, and programmed rules to inform and execute investment decisions. It surveys common components: historical and live market data,…
The document summarizes a study of factors associated with bilateral trade between Egypt and BRICS partners. It applies a gravity-model framework to panel data spanning 2001–2021, using information attributed to the World Bank and International Monetary…
This beginner-oriented guide explains machine learning through classification and house-price estimation. It distinguishes supervised learning, which uses examples with known outcomes, from unsupervised learning, which can group observations or identify…
The essay examines limits of using large language models and deep learning as autonomous trading decision makers. It contrasts their strength in finding patterns in historical data with the market researcher’s need to reason about current conditions, causal…
The article discusses how artificial intelligence and machine learning may affect trading, investment advice, and market structure. It describes machine learning as a way to identify economically useful predictive features and combine them with classifiers.…
This article outlines a machine-learning stock-selection experiment using TabNet and 98 price-and-volume factors. It trains the model on data from 2010 through 2018, then applies its predictions in a backtest covering 2018 through September 2021. The…
This tutorial outlines a machine-learning workflow for selecting Chinese A-share stocks with a convolutional neural network. It describes defining a stock universe and input factors, extracting and splitting data, turning observations into rolling sequences,…
This example outlines a daily workflow that combines browser-based research, trade review, and optional publication of a trade receipt. A research agent visits a configured site, captures evidence and a screenshot, and returns claims, contradictions, and…
This Chinese-language brokerage research summary examines advanced driver-assistance systems in China, focusing on adoption, technology requirements, supplier roles, and domestic competition. It describes ADAS as a chain of perception, planning, decision,…
This strategy uses a research agent to rank leveraged ETFs from recent prices and trends, then has bull and bear agents assess the same research. A judge and trading agent selects a side for each index, allocates the account among chosen funds, and revisits…
The document introduces naive Bayes as a classification method that applies Bayes’ theorem while assuming predictor features are conditionally independent given the class. It explains the roles of the class prior, feature likelihood, feature prior, and…
The document explains how to restrict a Chinese stock machine-learning dataset to shares that closed at their daily price limit, or to shares that hit the limit on the previous trading day. It describes filtering factor data by limit-status value and using a…
This guide explains how to monitor a StockRanker model’s validation performance during training. It recommends preparing a validation dataset, either from a separate data module or by reusing the training data, and connecting it to the model’s validation…
The speaker argues that quantitative investing should combine statistical description, machine learning prediction, and economic or financial theory. These serve different purposes: describing data, forecasting outcomes, and explaining underlying mechanisms.…
This research summary compares 17 machine learning approaches with conventional linear methods for predicting stock excess returns from 51 alpha factors. It describes splitting the prediction into two parts: an AR(1) forecast for return dispersion and a…
This review summarizes research applying machine learning to monthly and annual returns for Chinese A-shares. The study combines stock characteristics, macroeconomic variables, and industry indicators, then compares linear models, tree methods, and neural…
This overview explains how cryptocurrency trading bots automate decisions and trade execution using predefined rules. It describes several possible inputs: technical indicators such as moving averages and RSI, forecasts derived from historical data using…
This tutorial demonstrates a supervised learning workflow for hourly EUR/USD data using a k-nearest neighbors classifier. It builds features from price deviations from moving averages, moving-average spreads, momentum, Bollinger Bands, a sample sentiment…
This practitioner report describes experiments using a deep neural network to select stocks for a rapid rotation strategy. The model labels stocks by their subsequent return over a short holding interval, divides outcomes into ranked classes, and uses a…
This project description outlines a LightGBM system for classifying the direction of futures prices over a configurable forward horizon. It processes one-minute bars across multiple contracts, builds technical and statistical features, and labels future…