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.
5,922 documents
This strategy ranks U.S. stocks by return on assets (ROA) separately within larger- and smaller-capitalization groups. ROA is defined using quarterly income before extraordinary items divided by assets from the prior quarter. Within each size group, it buys…
This product guide explains a redesigned strategy interface with two parts: a viewer for examining and comparing strategies, and a creator for configuring new tests. The viewer presents performance metrics, behavior over time, and individual trade details.…
This study applies a factor-timing framework from a 2019 paper to China A-share data. It parameterizes factor weights using external variables and compares two approaches based on where the information enters: a time-series model and a cross-sectional model.…
This brief strategy description selects the 30 stocks with the smallest market capitalizations and allocates equal weights to them. It rebalances on the first trading day of each month and excludes ST-designated shares, the STAR Market, and the Beijing Stock…
This strategy ranks the full Chinese A-share universe using two cross-sectional signals: circulating market capitalization and five-day price momentum. It ranks each factor, adds the scores, and selects the highest-ranked 50 stocks. The portfolio assigns…
The document describes a monthly allocation rule based on a yield gap: the difference between an earnings yield measure for the S&P 500 and the yield on a ten-year Treasury bond. It fits a linear regression using historical yield gaps and stock market…
This article surveys three uses of unsupervised learning in investment research: manifold learning, clustering, and matrix factorization. For visualization, it applies t-SNE to fund returns, projecting high-dimensional observations into two dimensions so…
This report summary presents a method for setting equity allocations across a retirement investment horizon when the investor has a specified terminal wealth goal. It works backward from that goal, optimizing allocations while controlling risk. Two objective…
This article summarizes a study of machine-learning methods for fundamental equity valuation across 17 European countries. It estimates monthly fair values from 21 accounting variables, then defines a mispricing signal as the gap between model-implied value…
This research summary compares linear valuation models with machine-learning methods for estimating the monthly fundamental value of stocks in 17 European countries. It constructs a mispricing signal from the difference between estimated fair value and…
The article presents five claimed strengths of quantitative investing: building models from processed data and backtests, using machine learning to handle information, applying systematic rules to reduce emotional decisions, analyzing broad datasets, and…
This code excerpt describes two operations used in a cointegration-based statistical arbitrage workflow. The first multiplies each asset’s price series by the corresponding coefficient in a cointegration vector and sums across assets, producing a portfolio…
The paper combines return prediction and portfolio construction in a single neural network, aiming to reduce the decision errors that can arise when forecasts are optimized separately. It compares a model-free network, which learns allocations directly, with…
This introduction explains how cointegration can help create a mean-reverting portfolio from price series that are not themselves mean-reverting. By combining multiple assets with suitable weights, a trader may construct a spread or portfolio whose value…
The indicator described here creates an index for one of the eight major currencies from a configurable basket of as many as ten components. Users can select currency pairs or other instruments, turn each component on or off, and choose whether to invert the…
This configuration sets up a Qlib experiment that uses a gated recurrent unit model with Alpha360 features to rank CSI 300 constituents. Feature values are robustly normalized with outlier clipping and missing-value filling; labels use cross-sectional rank…
This implementation describes convergence trading for two cointegrated assets as a portfolio optimization problem. It estimates error-correction speeds and other model parameters from price data, then computes portfolio weights under both unconstrained and…
This article argues that grid trading can move beyond small gains by improving how the strategy handles falling markets. It describes combining suitable instrument selection, portfolio construction, dynamic grid placement, and position management to address…
This beginner guide explains convertible bonds as debt with interest and a right to convert into shares at a specified conversion price. It distinguishes the bond’s market price, the underlying share price, and the conversion price, then illustrates how…
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.…
The article reviews the long decline in mutual fund and ETF expense ratios and links it to investor choices, competition, and changes in financial advice and retirement plans. It distinguishes asset-weighted averages, which reflect where investors put their…
This research summary examines the difference between monthly stock and industry behavior in Chinese equities: individual stocks are described as showing reversal, while industry indices show momentum. It proposes an industry-momentum factor based on the…
This overview argues that no programming language is best for every algorithmic trading system. The choice depends on strategy frequency and volume, data needs, performance targets, development and maintenance costs, and the functions the system must…
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,…