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.
2,013 documents
The document describes a method for separating financial time series into processes that operate on different timescales. It frames the separation as generalized eigenvalue problems, using criteria based on variance and tail stationarity to identify slower…
The paper studies whether strategies built on non-equity assets can diversify algorithmic investment strategies tied to the S&P 500. It compares signals generated from LSTM forecasts, ARIMA-GARCH forecasts, momentum, and contrarian rules. The assets…
The document outlines a systematic approach to adapting trading strategies and asset allocation as market conditions change. It proposes using state-switching Markov autoregressive models to identify and predict regimes loosely associated with Wyckoff…
This work proposes RADAR, a retrieval-augmented diffusion framework for learning market state representations used in portfolio optimization under the stochastic discount factor framework. Its motivation is that markets shift between regimes, financial…
Tail-GAN is a data-driven scenario generator designed to simulate realistic joint price dynamics for high-dimensional multi-asset portfolios, with emphasis on losses in the tail of the distribution. It uses the joint elicitability of Value-at-Risk 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,…
This work describes systematic trading strategies driven by crisis indicators derived from the spectra of covariance or correlation matrices. One indicator family compares each date’s eigenvalue distribution with a reference distribution for calm or agitated…
This paper studies equilibrium prices and trading strategies in risk-sharing economies where heterogeneous agents face quadratic transaction costs. It characterizes the equilibrium with a coupled system of forward-backward stochastic equations, which jointly…
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…
This study uses a large-scale agent-based model to examine why urban housing markets experience rising prices followed by sharp corrections. It represents households as heterogeneous agents whose decisions remain economically rational while allowing…
The paper studies how to execute large orders across multiple assets when prices follow multivariate Ornstein–Uhlenbeck dynamics. It frames the trader’s objective as maximizing expected exponential utility of profit and loss, so the execution decision…
This study uses a lab-in-the-field experiment to examine how people guess whether financial markets will rise or fall. Volunteers receive controlled financial information based on real data from global indices and make repeated direction predictions. The…
This document proposes that randomness in market trades contributes to the stochastic behavior of prices and returns. It examines trade values and volumes over an averaging interval, treating them as random variables, and relates price and return volatility…
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 document presents a general workflow for designing, implementing, and assessing algorithmic trading strategies across stock and crypto markets. It uses four examples: a moving average crossover, a volume-weighted execution approach, sentiment-based…
This study uses a heterogeneous-agent framework to examine how trend-following and fundamental valuation can coexist in financial markets. It extends the Chiarella model with noise traders and a nonlinear demand response from fundamentalists. Bayesian…
The document presents a dynamic quantitative model intended to explain food price movements by combining supply and demand with investor behavior and corn-to-ethanol conversion. It argues that supply-and-demand explanations alone do not match the observed…
This study examines trend following across commodities, currencies, stock indices, and bonds over unusually long historical periods. It uses futures series available since 1960 and spot series extending back to 1800 for commodities and indices. After…
This study presents a graph-based spatial component for a large-scale agent-based model of urban housing markets. It represents how social and economic characteristics—including fear of missing out, tendency to follow trends, and the reach of an agent's…
This update extends a quantitative model of food prices through January 2012 without changing its structure. The original model was fitted to the FAO Food Price Index from January 2004 through March 2011. It includes investor trend-following, shifts of…
This work develops a trading strategy for an FX broker liquidating a large position in an illiquid currency pair. The broker trades a triplet comprising that pair and two liquid pairs, selected so that one pair is redundant. The setup is risk-neutral but…
This study addresses a variance double-counting problem in synthetic multi-asset equity data. When full asset-return generators are combined with a market factor, the simulated returns can include market variance twice. The proposed correction centers and…
The paper develops a model of multiple assets traded by investor groups with different strategies: some follow trends while others base decisions on fundamental value. It extends behavioral finance frameworks by representing finite cash and shares,…
The document describes momentum portfolios ranked with reward-risk measures derived from the classical tempered stable distribution. It compares these portfolios with traditional momentum across asset classes and markets, assessing returns alongside…