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 document describes an active strategy that shifts allocation between equal-weighted and capitalization-weighted equity portfolios. Its motivation is that equal weighting has often outperformed over long periods, but can lag when market concentration and…
The paper studies whether momentum information in one futures market can help predict momentum in others. It builds a network from price-derived momentum features across 64 continuously traded contracts in commodities, equities, bonds, and currencies,…
The document describes a data-driven sliding-window method for solving a log-optimal portfolio problem. Rather than assigning one fixed set of portfolio weights, the approach produces weights that vary over time. This offers a way to adapt portfolio…
The document presents L2GMOM, a machine-learning framework for network momentum. Network momentum uses relationships among assets to help predict future returns. The proposed framework learns the financial network and trading signals together, instead of…
This paper describes a model-less convolutional neural network that takes historical prices for a set of assets and outputs portfolio weights. It is trained through reinforcement learning, with cumulative return serving as the reward. The training data cover…
The paper addresses a portfolio-construction problem in statistical arbitrage: signals from many pairs can conflict, making it difficult to combine opportunities across a large group of securities. It proposes representing preference relations among…
The document studies portfolio growth optimization when expected asset returns are uncertain. It considers an incomplete, high-dimensional market in which asset prices depend on stochastic factors. Rather than fixing the drift completely, the framework…
The paper develops an adaptive matrix-variate Markov chain Monte Carlo method for Bayesian cointegrated vector autoregressions. It replaces griddy Gibbs sampling with an automated Adaptive Metropolis approach, intended to make posterior estimation practical…
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 paper examines how to estimate portfolio volatility and asset risk contributions over holding periods longer than one day. The familiar square-root-of-time scaling assumes returns are not serially correlated. Under that assumption, volatility…
These notes build a quantitative treatment of mean-reversion, beginning with pair trading and then progressing through demeaning, regression, weighted regression, constrained optimization, and factor models. The sequence shows how increasingly general…
This paper formulates optimal investment for an investor with constant relative risk aversion preferences in a continuous-time, incomplete market. Asset prices follow Itô processes, and trading strategies must satisfy dynamic risk constraints that vary with…
The document treats exchange quote-pair selection as an optimization problem: exchanges need to cover all currencies while prioritizing liquid pairs and limiting operational complexity. Because most possible pair volumes are unobserved, the proposed method…
This document examines how proportional transaction costs constrain leveraged investing in a market with one safe asset and one risky asset. It considers strategies designed to maximize long-term returns while maintaining an average volatility level, and…
The paper proposes Mid-LSTM, a deep learning model intended to predict stock prices over a midterm horizon while accounting for market anomalies. Its design represents market trends as hidden states. The described approach first formulates a midterm ARMA…
The paper develops a portfolio framework built around trend-following signals. It combines an autocorrelation model with the covariance of trends and risk premia, and specifies models for the trend covariance matrix. The resulting optimal portfolio is…
The paper describes a deep-learning approach to portfolio selection in US equities. Its residual switching network uses one module to identify market conditions and another to produce momentum and reversal forecasts, switching between the two types of signal…
This study examines optimal consumption and investment under power utility as relative risk aversion approaches two limiting cases: infinity and one. It establishes convergence results for optimal consumption in general semimartingale models, and for optimal…
This paper addresses how to construct a portfolio from underlying assets for use in statistical arbitrage, including pairs trading. The design seeks a portfolio with useful mean-reversion behavior while also controlling its variance, subject to an investment…
The paper evaluates how adding Bitcoin affects an internationally diversified portfolio using mean-variance optimization, conditional value-at-risk, and Markov regime switching. The first two frameworks indicate that Bitcoin can improve diversification, but…
This study examines optimal investment in two cointegrated stocks for an investor with constant relative risk aversion utility. It extends earlier stochastic-control work by focusing on whether the optimization problem is well-posed and by supplying a…
This work derives an approximate portfolio strategy for an investor in a simple incomplete market with a general utility function. It uses the Hamilton-Jacobi-Bellman equation for the value function and develops a first-order expansion in the length of the…
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 paper formulates a portfolio design problem for statistical arbitrage, seeking combinations of underlying assets with strong mean-reverting behavior. Its objective balances a criterion measuring mean-reversion strength against portfolio variance, while…