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 discussion addresses how to use factors from BigQuant's factor library as model features. The question asks whether a factor identifier can be used directly or whether users must copy its expression, and whether factors associated with a brokerage are…
This article introduces Granger causality and transfer entropy as ways to study directional predictive relationships in time series. Granger causality tests whether a source series improves forecasts of a target beyond the target’s own history, commonly…
This Chinese-language note describes a stock prediction exercise using four cross-sectional inputs: total market capitalization, turnover, trailing price-to-earnings, and quarterly net-profit year-over-year growth. It compares linear regression, XGBoost, and…
This configuration defines a Qlib workflow that trains an ordinary least squares linear model on Alpha158 features for CSI 500 stocks. The data spans 2008 through mid-2020, with training through 2014, validation in 2015–2016, and testing from 2017 onward.…
This document summarizes an introductory treatment of graph neural networks (GNNs), which learn from data represented as entities and their relationships. It explains how convolutional ideas used with images can be generalized to graph structures, whose…
The article argues that trading researchers should judge machine learning papers by simplicity, reproducibility, and generality, alongside reported empirical results. A method that performs well on a benchmark may not transfer to financial prediction, and a…
This study compares ARIMA, a multilayer perceptron, an LSTM, and an ARIMA-GARCH combination for next-day NVIDIA share-price forecasts. It describes ARIMA as a model for linear time-series structure, neural networks as ways to capture nonlinear patterns, and…
This interview discusses how artificial intelligence, large datasets, and cloud computing support one another: AI methods analyze data, while cloud infrastructure supplies scalable storage and computing. It maps the data industry across collection, storage,…
This introductory overview explains machine learning as using historical data to fit a model and then applying that model to new cases. A scheduling example illustrates how prior observations can inform a prediction, while noting that a practical model may…
The report estimates a fund’s equity exposure by regressing daily fund returns on daily returns for 29 first-level industry indices. It treats the sum of fitted industry coefficients as the estimated position. Because industry returns are correlated, it…
The document addresses a conflict between stop-loss logic and a machine-learning strategy's next-day buy list. A stock may be sold when it reaches a trailing stop, then selected again by the model on the following trading day. The proposed fix is to track…
This short research note discusses how machine learning might classify stock price patterns. It uses a triple-bottom formation to show why chart labels can be ambiguous: after a decline and consolidation with three lows, an upward break may confirm a…
This document describes a Chinese equity strategy research approach that uses supervised neural networks to generate many weak alpha factors from a set of input factors. It proposes transforming those outputs into low-correlation components, then weighting…
The indicator compares the current regression slope of closing prices with stored slopes from confirmed pivot highs and lows. A pivot is identified using highs or lows across a configurable window; the slope over the bars leading into each pivot is saved in…
The author outlines an index-enhancement approach for Chinese large-cap and blue-chip equities. First, a human-selected universe emphasizes historically strong companies and stocks that held up against the broad market during declines. A machine-learning…
This FAQ describes LumiBot, a Python framework for backtesting and live algorithmic trading across several asset classes and brokers. It outlines the shared strategy workflow, data-source requirements, and common operations such as handling fills, tracking…
This overview outlines a quantitative workflow: collect and clean data, develop a strategy, manage risk, backtest on historical data, and automate execution. It then sketches strategies for Chinese equities and futures, including Turtle-style breakouts,…
This overview explains decision trees as nonparametric models that divide observations through sequential feature rules. Each path defines a group, and a leaf assigns a prediction based on the labels in that group. The same feature can be used at multiple…
This brief Q&A explains how to change the scoring function used during hyperparameter search. The question asks how to include annualized return, win rate, and maximum drawdown alongside a Sharpe-based score. The response says the score function can read…
This speech transcript outlines a research framework spanning short, intermediate, and long horizons. It associates short-term work with factor models and machine-learning stock selection, intermediate work with industry and style rotation, and long-horizon…
This strategy combines model-based stock ranking with trend-following entry filters to seek short- and medium-term gains in Chinese equities. It starts from a manually selected pool of China Securities 150 constituents, narrowed to roughly 100–300 large,…
This expert-advisor design periodically searches recent price history for RSI or MFI thresholds that produced the greatest simulated monetary profit. It tests buy and sell signals separately across candidate indicator levels, using crossings of oversold and…
The document explains how combinatorially symmetric cross-validation (CSCV) can estimate the probability of backtest overfitting (PBO). It distinguishes training overfitting, where a model performs poorly on held-out data, from backtest overfitting, where a…
This introductory article presents ten practical points about machine learning for non-specialists. It emphasizes that machine learning finds patterns in data, so data quality, accurate labels, representative samples, and careful transformations often matter…