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.
4,194 documents
This study compares weekly stock momentum strategies in China using raw returns, idiosyncratic returns, and different measures of idiosyncratic risk. Its sample covers individual A-share stocks from January 1997 through December 2017. The authors first…
The study tests whether short-horizon price and volume signals developed for China’s A-share market add pricing information for S&P 500 stocks beyond established U.S. factors. It applies double-selection LASSO to assess signal loadings in a stochastic…
The document presents a discrete-time model of stock index returns built around the cyclically adjusted price-earnings ratio, or CAPE. Return growth combines momentum, a fundamental component tied to the logarithm of the initial CAPE, and a random driving…
The audit examines how to remove a predictor from regime-gated forecasts. Deleting a variable’s lagged inputs is not equivalent to excluding it from the full fitting, filtering, and tuning process, because the variable can also affect the estimated regime…
The document revisits how seven commonly studied company financial ratios relate to stock returns. It applies topological data analysis, specifically the Ball Mapper algorithm, to represent observations in the space of financial ratios as a two-dimensional…
The document evaluates the equity size effect using dollar turnover rather than market capitalization. It reports that a beta-neutralized and low-volatility-neutralized Cold-Minus-Hot portfolio remains significant over the long term, with a t-statistic of…
The study asks whether Fama–French equity factors help explain Bitcoin’s excess returns and idiosyncratic risk characteristics. It evaluates the factors’ explanatory power across different moving-average periods and applies several statistical methods to…
This article applies randomized controls to empirical asset pricing and investment performance evaluation. It uses geometric random walks, described as a class of Markov chain Monte Carlo methods, to generate random portfolios that satisfy investor…
The document studies how simultaneous trading in the same stock and direction can affect strategy performance, trading costs, and systemic risk. It proposes direct crowding measures based on fluctuations in trade imbalances, which can reveal when investors’…
The paper develops a way to test whether adding securities or relaxing investment constraints expands the opportunities available to investors who evaluate outcomes using prospect preferences. It formulates a test for prospect spanning between nested…
This document proposes Characteristic Vector Linkages as a proxy for relationships among firms. It uses characteristics to estimate linkages, first by measuring Euclidean similarity and then by applying Quantum Cognition Machine Learning to learn similarity.…
The document examines why the leverage effect, despite being widely observed, may have little apparent influence on the return distributions of some assets. The leverage effect describes a generally negative relationship between asset returns and changes in…
The paper evaluates whether macro and market signals can time allocations between growth and defensive ETF baskets. It frames the task as style allocation rather than discovery of a new alpha factor: factor attribution finds that the growth-minus-defensive…
This study builds a statistical arbitrage method around a conditional factor model for a portfolio of US equities. A state space model treats returns as noisy combinations of factor values and latent, time-varying factor risk premia. Online filtering and…
The paper proposes distance-based measures for comparing asset pricing models, motivated by concerns that statistical tests may have low power and that alpha statistics can be used without discipline. The proposed metric combines squared alphas and squared…
The paper examines how trend systems operating over different horizons contribute to commodity trading advisor (CTA) returns. It proposes a Bayesian graphical model to dynamically separate returns into short-term trend, long-term trend, and market beta…
This study proposes a stock portfolio method based on predicting the distribution of residual factors, which capture information beyond common market exposures and can help hedge those exposures. It describes two main components: a computationally efficient…
The study examines whether factor momentum contains return information beyond stock momentum. Using a sample of 72 factors reported in prior literature, it first reproduces evidence for both directional and cross-sectional factor momentum. It then applies a…
The paper proposes four factors for explaining or predicting overnight returns, constructed from intraday price and volume data. The factors are designed as short-horizon analogues of size, volatility, momentum, and liquidity. Long-horizon fundamental…
The document describes deep partial least squares (DPLS), a model for explaining individual stock returns using a small set of latent risk factors and firm characteristics. Projected least squares jointly maps returns and characteristics into a latent factor…
This study examines a low-minus-high rank effect in commodities: lower-priced, lower-ranked commodities have higher subsequent returns than higher-ranked ones. Using nonparametric econometric methods, it argues that this effect follows from a stationary…
This study tests whether sentence-level context improves news topic models used to build systematic asset-pricing factors. It compares Latent Dirichlet Allocation with a frozen sentence transformer followed by k-means clustering, using the same collection of…
This paper proposes a two-factor asset-pricing model for economies where firm capitalizations have a sufficiently heavy-tailed distribution. Alongside conventional market risk, the model includes diversification risk, proxied by an equally weighted…
This paper examines how investors’ beliefs and asset prices may be distorted when their learning model understates structural breaks in factor risk premia. It proposes a minimal Bayesian framework in which this misspecification creates persistent forecast…