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.
4,574 documents
The document proposes mapping real exchange rate movements onto a string-like structure to build forecasting models for forex trading. It argues that conventional long-horizon econometric approaches can miss practical features such as transaction costs,…
The document explains how fractional Brownian motion (fBm), whose non-overlapping increments can be dependent, may support forecasts of future price changes. If log-prices follow this process, its non-Markovian structure can provide information for…
This study analyzes one-minute Bitcoin returns to describe their distribution, behavior across sampling intervals, volatility asymmetry, and multifractal properties. It reports fat tails and kurtosis far from the Gaussian benchmark, with kurtosis approaching…
The document describes a long-only USD/TWD trading agent that combines Quantum Long Short-Term Memory (QLSTM) forecasts of short-term trends with Quantum Asynchronous Advantage Actor-Critic (QA3C). Its state uses QLSTM features and technical indicators,…
This paper tests whether the local volatility model is useful for hedging AUD/USD vanilla options. Local volatility extends Black-Scholes by allowing volatility to depend on time and the underlying exchange rate, and it can be calibrated to fit an…
The paper builds a microscopic account of financial price motion from observations of high-frequency traders in a foreign exchange market. It tracks individual trader trajectories and reports a collective trend-following pattern that conventional order-book…
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 paper addresses pricing American and Asian options in foreign-exchange derivatives markets, where banks use complex models and different model choices can produce inconsistent prices for the same exotic contract. The authors study a fully parameterized…
The document introduces the Epps Effect: correlations between returns on related assets generally rise as the return horizon gets longer. It then describes a reported departure from that pattern in foreign exchange and cryptocurrency markets. The specific…
The study tests the weak form of the efficient market hypothesis for Bitcoin with a feedforward neural network. It asks whether adding returns or related features from other assets improves prediction, alongside Bitcoin returns. The additional inputs include…
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 uses an agent-based model to explore how correlations between exchange rates can arise in foreign exchange markets. It focuses on interactions between market makers and an arbitrager exploiting triangular price relationships. The motivation is…
The document develops a trading strategy with trailing stops under the assumption that currency exchange rates behave in a mean-reverting way similar to Ornstein–Uhlenbeck processes. It derives an explicit expression for the running maximum of an…
The document presents a hybrid dynamical model for studying trend-following behavior in currency markets. It generates symbolic dynamics from a lognormal diffusion model of the at-the-money implied volatility term structure, using information from…
The paper examines transitions between mean-reverting and momentum regimes through two nonlinear mechanisms: slow and fast bifurcations. In the slow case, an evolving equilibrium is preceded by a delay in the loss of stability as a control parameter changes.…
The document introduces a framework for judging whether an autonomous trading strategy is likely to remain reliable beyond a historical simulation. It focuses on common evaluation pitfalls that can make a strategy look successful in backtests but perform…
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,…
This study applies deep reinforcement learning to foreign exchange trading, framing trade choice as a sequence of decisions rather than relying on direct price forecasts. It adapts a Sure-Fire statistical arbitrage policy into three possible actions and…
This document introduces the Visibility Graphs Relative Strength Index, a price-based indicator built from backward visibility relationships in an instrument’s price series. The indicator is scaled from zero to 100 and used to generate signals in an…
The document describes a mean-reversion approach that begins with yield-curve trading strategies and extends the idea to a multi-pair strategy involving major currency pairs. To refine its trading signals, the strategy incorporates machine-learning forecasts…
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 study examines whether Bitcoin, Ethereum, and Ripple had stable daily dollar returns relative to the euro, Japanese yen, the S&P 500, and the MSCI World Index over the sample period from 2016 to 2020. It first removes cycles shorter than one month, then…
This work introduces multidimensional string-based objects as tools for forecasting financial time series. It describes open strings with two endpoints and D2-branes as extensions of an earlier single-endpoint string model, and examines how their properties…
The document outlines a proposed USDCHF trading strategy that uses gold market dynamics as an intermarket filter. It models both markets with a coupled hidden Markov model, linking their state behavior rather than analyzing the currency pair in isolation.…