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.
19 documents
This short discussion considers the role of foreign exchange in a systematic trading portfolio. Its central claim is that FX does not offer an inherent risk premium that can provide a persistent return tailwind, so traders must seek returns through active…
The article explains how an autoregressive model predicts the next exchange-rate value from prior observations, then examines whether those predictions could support AUD/USD trades. It discusses partial autocorrelation across several sampling intervals, fits…
The article demonstrates how to estimate historical FX rollover payments using central bank policy rates, a broker charge, and currency conversion. It implements the calculations in both Zorro and Python. The long and short roll estimates depend on the…
This article uses k-means clustering to group daily GBP/JPY candles according to their high, low, and close relative to the open. It examines whether particular candle clusters tend to follow one another and whether returns after each cluster differ. The…
This tutorial demonstrates a basic feed-forward neural network workflow for classifying the direction of hourly foreign exchange price changes. It constructs features from hourly changes in closing, high, and low prices, along with distances among those…
This note applies lessons from gambling to strategy selection. It recommends looking for comparatively tractable opportunities, including harvesting risk premia and predicting relative returns across assets rather than forecasting the absolute direction of…
This guide introduces the perceptron, a basic neural network model for binary classification. It outlines activation functions and learning, then demonstrates how weights and a bias can be updated from classification errors. Examples use iris flower…
The article outlines a framework that groups daily candle patterns with k-means, then tests whether particular clusters support long or short trades. Its sample features are the day’s high, low, and close relative to its open. Historical observations are…
The article examines whether EUR/USD shows a repeatable return pattern around the US non-farm payroll release, scheduled for the first Friday of each month. It describes plotting average cumulative returns across the morning window from 6:00 to 11:00 Eastern…
This article describes techniques for reducing overfitting in feed-forward neural networks used to forecast market direction. It outlines L1 and L2 regularization, which penalize large model weights, and dropout, which randomly disables units during…
The document explores whether currency prices can form stationary spreads suitable for mean-reversion analysis. It estimates a two-currency spread using ordinary least squares, then tests the residual with an augmented Dickey-Fuller procedure. It also…
The document outlines an experiment for studying how training-window length and predicted class-probability thresholds affect a financial prediction strategy. It constructs directional labels from returns and uses lagged returns and volatility measures as…
The article introduces digital signal processing concepts for trading, including cycle period, frequency, amplitude, and phase. It explains how low-pass, high-pass, and band-pass filters emphasize or suppress different cycle lengths, and how stacking filters…
This article demonstrates an unsupervised approach to grouping GBP/JPY candles by their shape. It represents each candle using the high, low, and close relative to the open, then applies k-means clustering with six groups. The assigned cluster labels are…
This article explains ARIMA models for forecasting a time series’ mean and GARCH models for its changing conditional variance, then combines them in a directional EUR/USD strategy. It fits models to a rolling window of daily log returns, selects ARIMA orders…
Carry is a position expected to earn a return as time passes, provided prices and other conditions remain stable. The document explains this through currency yield differentials, rolling bond and stock futures, and selling options, then describes perpetual…
The document presents a Cold Blood Index intended to help a systematic trader judge whether a live drawdown is unusual enough to warrant leaving a strategy or whether continuing may be reasonable. The supplied code reads a historical balance curve, resamples…
This article outlines a way to assess whether a strategy’s backtest results stand out from outcomes generated by chance. It proposes constructing randomized strategies that match the original strategy’s simulation period, trade count, direction, and average…
This article introduces several ways to assess whether an exchange-rate series may suit a mean-reversion strategy. It explains the Augmented Dickey-Fuller test as a check for a unit root, the Hurst exponent as an indicator of trending or reverting behavior,…