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.
1,116 documents
This study examines whether cryptocurrency exchange rates moved independently of traditional foreign exchange rates. Using high-frequency Kraken records from July 2016 through December 2018, it analyzes multiscale cross-correlations among Bitcoin, Ethereum,…
The paper models how an asset’s price forms when it is traded through an order book. It develops two related approaches: a finite many-person game and a mean-field game, with trading costs that reflect limited liquidity. In both frameworks, the authors…
The paper presents a model of tick-level financial returns that combines an ARFIMA process, bid–ask bounce, fat-tailed returns, and non-Poisson trade intervals. It uses these ingredients to explain several observed features of market data: brief correlations…
This analysis examines tick-level data from major cryptocurrencies traded on multiple platforms. It studies the time between transactions alongside transaction counts, trading volume, and volatility. The authors report long-range power-law autocorrelation in…
The study models how the severity of extreme losses in high-frequency markets changes with trading activity and market uncertainty. Its dynamic extreme value regression accommodates both stationary and local unit-root predictors, addressing predictor…
This research examines high-frequency observations from European cryptocurrency markets to characterize intraday activity associated with algorithmic trading. It analyzes returns, trading volumes, periodic patterns in volatility, and return correlations with…
This paper proposes a deep recurrent model that uses exchange order flow to model directional price movements at high frequency. Order flow is described as the stream of arriving orders that contributes to price formation. The central question is whether a…
This study examines high-resolution USD-JPY exchange-rate data spanning 13 years. Its focus is on statistical patterns in the distributions and correlations of exchange-rate changes, with particular attention to whether price movements depend on recent…
This document updates the Glosten–Milgrom model of informed and uninformed trading to examine how automated liquidity providers affect markets. The revised framework includes multiple securities and an automated market maker that uses relationships among…
The document describes a cryptocurrency trading system that combines trend information across multiple timeframes with neural networks that predict near-term price direction. It brings market prices, on-chain measures, and order-book activity into a shared…
ClusterLOB groups individual market events from market-by-order data using six time-dependent features and K-means++ clustering. The resulting groups are interpreted as directional, opportunistic, and market-making participants, providing a way to study…
The paper presents a theoretical model that links trading conditioning intensity with security price volatility and returns. It uses distributions of transaction volume and price to represent uncertainty and intensity, framing the relationships in terms of…