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.
1,414 documents
The study examines pairs-trading extensions across Brent, WTI, and Shanghai crude oil futures. It reports that the three price series are cointegrated and models their resulting spread as mean-reverting with regimes governed by a hidden Markov chain. Online…
The document examines option pricing and hedging on energy forwards when spot prices follow a geometric multifactor model with several mean-reversion rates. It focuses on how slow mean-reverting components affect valuation and hedge quality. The authors…
This paper compares fixed stock-and-bond and stock, bond, and gold allocations with long-only dynamic portfolios that may also hold cash. The portfolios use public data, rebalance monthly, and are assessed using return, volatility, excess Sharpe ratio,…
The paper presents a generative neural network for probabilistic forecasts of intraday electricity prices in Germany’s continuous-time market. Instead of producing only a point estimate, the method generates possible price paths and uses them to inform…
The paper studies what drives futures price volatility and basis for gold, oil, and bitcoin using a contract-by-contract approach. It analyzes daily spot and futures prices alongside maturity, trading volume, and open interest over the period from December…
The document outlines a study of hybrid approaches to forecasting spot electricity prices in the EPEC market. The model components include a naive forecast, Fourier analysis, ARMA and GARCH models, a mean-reverting jump-diffusion process, and recurrent…
The document describes a systematic trend-following strategy for commodity futures that combines conventional single-market trend indicators with cross-market signals. These cross-sectional signals aim to capture momentum spillover, where trends in one…
The paper presents a method for operating and valuing electricity storage when intraday prices are uncertain. It formulates the charging and discharging problem as convex stochastic optimization and uses Stochastic Dual Dynamic Programming to solve it. The…
The document presents a practical deep reinforcement learning approach for trading natural gas futures. It reports that the strategy’s Sharpe ratio exceeds trend-following and mean-reversion benchmarks, as well as results from prior literature. It also…
This paper presents a method for computing a first-order approximation to the prices of derivatives on futures under multiscale stochastic volatility. It offers an alternative to a singular perturbation approach and is designed to work without additional…
This study tests a pairs strategy on spot prices for 17 Indian commodities across energy, metals, and agriculture from 2010 through 2018. It uses Johansen cointegration tests on the training sample to select long-run related commodity pairs, then models each…
The study examines liquid commodity futures traded in Chinese markets before and after the onset of Covid-19. It compares empirical return moments and cointegration across products, motivated in part by the relevance of cross-commodity relationships to pairs…
The study compares Bitcoin with gold and the S&P 500 using daily, weekly, and monthly closing prices and log returns from September 2014 to January 2021. It distinguishes volatility measured by standard deviation from predictability measured by approximate…
The paper examines how trend systems operating over different horizons contribute to commodity trading advisor (CTA) returns. It proposes a Bayesian graphical model to dynamically separate returns into short-term trend, long-term trend, and market beta…
This paper extends a mean-reversion trading framework with stop-loss rules and leverage. It models security prices as an Ornstein–Uhlenbeck process and evaluates repeated trades through a self-financing portfolio, accounting for proportional transaction…
This study predicts short-term directional changes in a futures contract using features drawn from technical analysis, order flow, and order-book data. It trains a TabNet deep learning model on silver futures listed on the Shanghai Futures Exchange,…
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 hourly Czech electricity prices from 2009 to 2012, focusing on long-term memory in a series with strong intraday and daily cycles. To account for those cycles, it applies detrended fluctuation analysis, a method suited to examining…
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 study examines a low-minus-high rank effect in commodities: lower-priced, lower-ranked commodities have higher subsequent returns than higher-ranked ones. Using nonparametric econometric methods, it argues that this effect follows from a stationary…
This study develops a day-ahead bidding and operating policy for a hybrid plant that combines wind generation with an electrolyzer. The policy sets power bids and schedules hydrogen production using contextual information, with linear decision rules learned…
The study examines whether better probabilistic day-ahead electricity price forecasts translate into better battery trading outcomes. It identifies two limitations of quantile-based trading strategies: they do not reward honest probabilistic forecasts, and…
The study applies diffusion entropy analysis to Nordic spot electricity prices, a market shaped by varied influences but also exhibiting familiar speculative-market behavior such as clustering and mean reversion. It examines the waiting times between…
The paper proposes a model for electricity prices under a price-cap principle, representing the asset price as an exponential functional of a jump Lévy process. The chosen process is intended to capture both mean reversion and jumps, features associated with…