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.
5,922 documents
The article outlines a process for assessing automated trading systems offered in a marketplace. It recommends understanding whether an Expert Advisor acts on ticks, new bars, or a timer, because operating logic affects how it should be tested and how…
This article explains an interpretation of the Artificial Bee Colony (ABC) algorithm, a population-based method inspired by how honey bees search for food sources. Candidate solutions represent locations in a multidimensional search space, and the objective…
The article presents MASAAT, a portfolio optimization framework that combines multiple agents, directional price filters, and attention mechanisms. Agents use filters with different thresholds to extract trends at different scales. Cross-sectional attention…
This installment improves an automated workflow for turning strategy optimizations into a multi-currency expert advisor. The pipeline first optimizes one strategy across symbols and timeframes, selects promising individual instances, then searches for groups…
This article explores automating the selection of optimized strategy instances for a multi-currency Expert Advisor. It first prepares optimization data, removes loss-making results, and ranks candidates with a weighted score built from scaled performance…
The article explains the Sharpe ratio as average return above a risk-free rate divided by return standard deviation. It outlines how to compute periodic returns and dispersion, and how to annualize ratios from shorter timeframes using the square root of the…
The article revises the design of a multi-currency Expert Advisor that runs multiple strategies. Its initial architecture lets each strategy place market orders directly, which can leave some strategies unable to trade when position sizes fall below broker…
The article describes an MQL5 graphical interface for reviewing Expert Advisor optimization results. It presents a sortable table of top-performing passes, stores summary statistics alongside total and per-symbol balance data and drawdown series, then lets a…
This article proposes evaluating social trading signals by inspecting the trades that generated their reported returns, rather than relying only on headline growth, subscriber count, and drawdown. It defines entry quality using maximum adverse excursion…
The article describes portfolio allocation in Python and MQL5 using historical daily prices from MetaTrader 5. Its Python example calculates asset returns, estimates average returns and covariance, then maximizes expected return minus a variance penalty…
This article describes a tool that measures the relationship between two currency pairs, using EUR/USD and GBP/USD as its example. It explains correlation coefficients from negative to positive values and discusses how strongly related pairs can create…
The article argues that signal quality should be judged by the stability of returns and risk, not by a smooth balance curve or subscriber count alone. It warns that changing position sizes can disguise weak trade performance, and recommends examining results…
In this interview, Automated Trading Championship participant Valery Mazurenko describes building a multi-currency expert advisor from simple entry rules, then using optimization to select logical combinations of those rules. The system combined seven or…
The article introduces category-theory products as a way to pair values from two indicator domains while retaining each value, then illustrates the idea in an MQL5 expert-advisor signal class. DeMarker and Williams Percent Range readings are mapped into long…
The article adapts three opening range breakout strategies from Concretum Group research for intraday trading of a Nasdaq-100 CFD. It describes opening-period signals, moving-average and VWAP filters, stop placement, position risk, and end-of-day exits. The…
This article extends an MQL5 table library built around the Model-View-Controller pattern with a vertical row header, complementing the existing column header. It applies the updated interface to an indicator that displays a symmetric correlation matrix for…
This installment describes preparing a multi-currency expert advisor for real use by extracting selected strategy-group initialization data from a large optimization database and packaging it with the EA. The workflow has three stages: select groups and save…
The article presents the Eco-inspired Evolutionary Algorithm (ECO), a population-based metaheuristic that searches with multiple evolving subpopulations. It periodically groups populations into habitats according to the distance between their centroids.…
In this interview, Mariusz Zarnowski discusses his development as an automated forex trader and his 2012 Automated Trading Championship system. He describes moving from single-currency Expert Advisors to multi-currency systems, with different moving-average…
This work studies infinite-horizon investment and consumption for an investor with power utility in an incomplete market whose opportunities depend on a stochastic factor. It treats both finite-state factors and factors modeled as Itô diffusions, connecting…
This paper studies portfolio choice over an individual’s life when income is stochastic and investments include stocks, a bond, and life insurance. The objective accounts for consumption, death benefits, and terminal wealth. A convex trading constraint…
The article explains the Deep Momentum Network (DMN) approach to multi-asset trend following. Rather than predict returns and determine portfolio weights separately, the model outputs each asset’s next-period position, bounded between long and short…
This guide outlines an end-to-end quantitative research workflow using Qlib. It describes installing the library, preparing Chinese market data from public sources, and running an example LightGBM configuration with the qrun tool. That workflow combines…
The code implements a statistical-arbitrage strategy that uses a fitted C-vine copula to estimate conditional probabilities for a target asset from a panel of returns. It transforms each asset’s returns through fitted cumulative distribution functions,…