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.
67 documents
This analysis asks whether futures with more negative return skew earn higher returns, both across assets and when skew changes over time. It estimates skew from percentage returns after filtering extreme volatility-normalized observations, then uses…
This document outlines three futures trading rules built from skew and kurtosis: a standalone skew signal, skew conditioned on kurtosis, and kurtosis conditioned on skew. Signals are normalized by a robust volatility estimate and smoothed; conditioned…
This career guide explains that quantitative and systematic trading covers many assets, holding periods, strategies, and degrees of automation. It notes overlap with related roles such as risk management, portfolio management, execution, quant development,…
This portfolio-optimization study compares four ways to estimate forecast weights: fitting each instrument separately, pooling all instruments, pooling within asset classes, and grouping instruments by similarity in portfolio weights. The author describes…
This document compares ways to include trading costs when optimizing portfolio or forecast weights. Options include optimizing gross returns, subtracting costs to form net returns, optimizing costs alone, penalizing costs by a multiplier, applying a maximum…
This post revisits a dynamic portfolio optimizer that traded too frequently when first implemented. The author identifies shortcomings in the turnover and cost estimates, especially for sparse portfolios where many instruments have zero positions. Because…
This document explains how synthetic data can help investigate trading systems when historical observations are too limited to support strong conclusions. It distinguishes simulated price paths for testing individual rules, correlated asset-return series for…
This outline describes a study of trading an equity curve: reducing a system’s exposure after weak performance and restoring exposure when a simulated account recovers. It frames the approach as an overlay with separate rules for detecting poor performance,…
This note asks whether markets that perform well for trend-following do so because their prices have drifted favorably, because of carry, or because they convert those effects into trend signals more effectively. It compares bonds, foreign exchange, metals,…
The post develops a framework for thinking about the compensation investors should require for taking on risk, focusing on standard deviation and skew. It evaluates investments by geometric growth or final wealth at selected points in the return…
The document explores how a regression’s R squared can be related to the Sharpe ratio of a trading forecast. It presents three routes: a closed-form relationship based on the law of active management, simulations using random price series, and analysis of…
The document introduces factor analysis as a way to understand the sources of risk and return, then contrasts predefined equity factors with the less obvious drivers of returns across futures markets. It reviews possible uses of factors, including taking…
The document compares Average True Range (ATR) with standard deviation as measures related to market movement. Standard deviation is based on close-to-close returns and centers observations around their average, then squares deviations before averaging and…
The author investigates whether momentum performance and the preferred trading speed vary with instrument trading costs. Two competing ideas are considered: gross performance may be similar across instruments, leaving expensive markets less attractive after…
The document describes an experiment comparing clustered and unclustered portfolio optimization across trading rules and instruments. It varies in-sample and out-of-sample periods, the number of assets, correlation shrinkage, Sharpe ratio shrinkage, and the…
The document explains how diversification across futures markets can increase the risk-adjusted performance of systematic strategies. It defines effective independent bets by comparing a portfolio’s risk reduction with what would result from the same number…
The author checks whether a heuristic hierarchy for allocating forecast weights across trading rules is supported by correlations in rule returns. To build the correlation matrix, each rule is treated as a portfolio across the instruments actually weighted…
The document explains top-down replication of a managed futures index: estimate positions in a basket of futures by regressing index returns on instrument returns. Although a long history may seem to support a regression with many instruments, positions…
The document explores three changes to fitting trading-system weights: exponential weighting that emphasizes recent performance, evaluating alpha rather than Sharpe ratio alone, and jointly fitting instrument and forecast weights. The motivation is that old…
The document proposes selectively pooling return histories across instruments when their estimated Sharpe ratio profiles across trading rules appear sufficiently similar. It describes a clustering procedure: estimate each instrument’s Sharpe ratios, measure…
The document distinguishes explicit, implicit, and tacit overfitting in trading research. Explicit overfitting comes from fitting too many parameters to historical data; suggested controls include reducing degrees of freedom, using robust fitting, and…
The author questions whether Bitcoin’s positive skew alone justifies very large portfolio allocations, using a published allocation claim as a starting point. The post compares the intuition behind holding Bitcoin with the appeal of lottery-like payoffs,…
The document explains positive skew as a return pattern with frequent small losses and less frequent large gains, then examines whether trend-following strategies display that pattern. It relates trend following to a lookback straddle: both can benefit from…
The document outlines a Python-based workflow for calculating UK trading tax liability from trade and position source files, with configurable output, foreign exchange data, calculation method, and reporting detail. It describes several verbosity levels,…