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 report describes a stock-selection approach that optimizes portfolio weights while constraining market-cap, industry, and style exposures. Its goal is to retain exposure to alpha factors while limiting unwanted variation from other risk factors. The…
This note outlines two ways to include industry or sector membership in stock factor research. One approach treats each industry or sector as a grouping variable and compares the cumulative returns of its constituent stocks, effectively studying group…
This 2020 research summary analyzes the Silver Hua CSI Innovative Drug Industry ETF and its underlying index. The index selects up to 50 listed companies associated with innovative drug research, ranked by market capitalization. The report discusses the…
This tutorial section explains how to implement a cross-sectional momentum strategy, commonly called Up Minus Down, in Moonshot, an open-source vectorized backtester that uses pandas. The example ranks securities by returns over a 252-day momentum window…
The document introduces the case for identifying actively managed industry theme funds in China’s A-share market. It describes pronounced differences in industry returns and rotation over the prior decade, with some sectors producing strong gains even when…
This survey introduces supervised, unsupervised, semi-supervised, and reinforcement learning, then outlines common methods such as neural networks, support vector machines, nearest neighbors, clustering, and Bayesian networks. It places machine learning in…
This survey introduces supervised, unsupervised, semi-supervised, and reinforcement learning, then outlines common methods such as neural networks, support vector machines, nearest neighbors, clustering, and Bayesian networks. It places machine learning in…
This article explains a holdings-based panel regression approach to evaluating mutual fund performance. With stock fixed effects, a conventional performance measure can be separated into time-series ability (TSA), reflecting whether changing portfolio…
This review examines whether published indicators of future mutual-fund performance retain their predictive power outside the periods in which they were studied. It compares high-minus-low portfolio alpha spreads and cross-sectional regression slopes across…
This Chinese equity screening proposal selects main-board stocks whose MACD is above zero and whose price has gained more than 1% on the day, while restricting company establishment dates to 2021. The article explains each condition as a way to combine…
This research roundup summarizes two studies. The first compares the Fama–French five-factor model with a version that adds momentum, then considers replacing the standard value factor with a more immediate value measure. The summary says the six-factor…
This research summary argues that broker stocks deserve separate modeling within CSI 300 enhancement portfolios because the sector has a meaningful index weight and tends to move differently from other industries. It tests stock-selection factors within the…
This Chinese-language competition update reports diagnostics for the ten highest-ranked anonymous factors and tracks a CSI 1000 index-enhancement portfolio. It describes average style exposures estimated through daily multivariate regressions and…
The document describes a macro allocation framework built from six risk factors covering growth, inflation, rates, credit, foreign exchange, and term spreads. It combines momentum signals with cycle-phase estimates, maps the resulting states into…
The report outlines a multi-asset allocation framework that links macroeconomic risks to broad asset classes, styles, and industries. It identifies economic growth, interest rates, exchange rates, inflation, and credit as five central risk factors. A…
This research review applies conditional generative adversarial networks (cGANs) to multi-asset allocation. It conditions the model on recent asset-return sequences and random inputs to generate possible future paths, then estimates expected returns and…
A VeighNa community exchange addresses two backtesting questions: whether multi-contract portfolio and CTA backtest modules expose account net value, and how to display or save CTA-style trade records and candlestick charts after a portfolio backtest. The…
This report summarizes quantitative approaches to enhancing returns over Chinese equity benchmarks while managing tracking error. It frames enhancement as a blend of active and passive investing and describes a top-down range of choices: market exposure,…
This document outlines a monthly long-only stock selection strategy for the Chinese A-share market. It ranks the universe using a market-cap rank and a 20-day average of price changes, combines the two into a score, then holds 50 equally weighted stocks with…
This report describes an initial step in building a multi-factor equity model: choosing which factors to combine. It proposes reducing the factor search space by including exposure relative to a benchmark as one screening criterion, alongside the strength of…
This configuration defines a Qlib equity forecasting workflow using the CSI 300 universe and the Shanghai CSI 300 index as benchmark. It sets a data window from 2008 through 2020, with training through 2014, validation over 2015–2016, and testing over…
This review examines the low-risk effect: securities with lower measured risk have historically delivered stronger risk-adjusted returns than the standard CAPM relationship would predict. It explains betting against beta (BAB), which leverages a low-beta…
This research summary compares two ways to incorporate analyst expectations into equity selection. A parallel approach blends forecasts with other factors or uses them jointly to predict returns. The proposed serial approach first builds a conventional…
This report tracks equity factors using information coefficient (IC) summaries and the relative returns of factor-ranked long portfolios. It describes ranking stocks by factor values, selecting the top decile for each factor, and weighting holdings by the…