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.
5,018 documents
The article proposes a trading signal that compares normalized price slope with an indicator slope over a lookback window, then treats their difference as structural divergence. It combines this measure with a three-horizon attention proxy intended to weight…
The article explores using neural network activation functions to build custom criteria for ranking strategy parameter sets in MetaTrader optimization. It argues that returning zero for an undesirable pass can disrupt genetic search, while unrestricted…
This article surveys preparation and selection of input variables for machine learning, with examples aimed at financial data. It recommends handling missing observations, checking near-constant predictors, reducing problematic correlations where…
The article explains how Twin Delayed Deep Deterministic Policy Gradient (TD3) modifies DDPG to reduce overestimation of learned Q-values. Its three core changes are training two Critics and using the lower estimate, updating the Actor less often, and…
This article presents TimeFound, a Transformer framework for forecasting time series across domains, and discusses how it can inform systematic trading. The model represents data at multiple time scales by splitting histories into patches of different…
This tutorial demonstrates a compact market-data learning pipeline using MQL5's ALGLIB data-analysis library. It converts OHLC bars into five numerical features—one-bar return, candle-body ratio, range ratio, and two momentum measures—and labels each…
This article applies the category-theory idea of a natural transformation to time-series forecasting with differently structured datasets. One dataset contains a moving-average value; another contains the constituent lagged prices. The author treats the…
This article continues an MQL5 implementation of CATCH, a neural approach to anomaly detection in multivariate time series. CATCH transforms series with the Fourier transform, divides the spectrum into frequency patches, and uses complex-valued convolutions…
This tutorial shows how to build a basic neural-network trading Expert Advisor by connecting MetaTrader 5 with NeuroPro, a multilayer network tool. It exports EURUSD hourly closing prices to CSV, converts the data to DBF for NeuroPro, trains and tests a…
This article introduces Deep Deterministic Policy Gradient (DDPG) as a reinforcement-learning approach for trading agents that must choose continuous action values. Instead of expanding a discrete action list for every combination of direction, volume, stop…
The article presents Animal Migration Optimization as a population-based method for searching an objective function. Each candidate solution is treated as an animal in a ring-structured neighborhood. During migration, an animal selects a neighbor and moves…
This article describes an MQL5 implementation of the truncated Newton conjugate-gradient method for minimizing functions with or without box constraints. Rather than construct and store a full Hessian, the method uses an inner conjugate-gradient process and…
The article describes a short-term recommendation system that combines Singular Spectrum Analysis (SSA) forecasts with Bayesian classification. It builds three SSA-based indicators for trend, MACD-like direction and stochastic behavior, then groups their…
The article presents a forex prediction system inspired by quantum computing, moving from a Python prototype using Qiskit to a classical approximation implemented in MQL5. In the prototype, market features are encoded with rotation gates, entangling gates…
The article explains why ordinary bootstrap sampling can be a poor fit for financial machine learning when labels cover overlapping time intervals. Repeatedly sampling with replacement may select observations that encode much of the same market event,…
This beginner guide introduces the concepts and tools needed to start programming in MQL5. It defines basic computer terms, explains the roles of an editor, compiler, debugger, version control system, and integrated development environment, then compares the…
The article describes an MQL5 statistical library that provides descriptive measures such as mean, variance, skewness, kurtosis, median, and deviations, alongside functions for many continuous and discrete probability distributions. For each supported…
This article explains how a Hidden Markov Model represents a time series through unobserved states, state transition probabilities, initial state probabilities, and state specific observation distributions. It describes forward and backward likelihood…
The article introduces clustering as a way to group similar financial observations, then discusses two applications: identifying volatility based market regimes and grouping trades or time series to account for heterogeneous effects. It surveys methods…
This tutorial introduces matrix and vector operations for readers new to linear algebra, using MQL5 examples to contrast element-by-element loops with matrix methods. It argues that matrix operations can make code more concise and maintainable, and may…
The article introduces regularization as a way to limit neural-network overfitting by adding a penalty related to model weights during training. It compares L1 (Lasso), L2 (Ridge), and dropout, and discusses how the choice may depend on whether a network…
This article explains the Cuckoo Optimization Algorithm, a population-based heuristic for continuous nonlinear optimization. Candidate solutions are represented as eggs in nests and scored with a fitness function. Each iteration generates new candidates…
The article explains how quantile regression can represent the distribution of future rewards in distributed Q-learning. Earlier distributional approaches divide reward values into fixed ranges, which can waste model capacity on ranges with no observed…
The article describes an end-to-end workflow for training a model to screen EMA crossover trades and deploying it in an MQL5 Expert Advisor. It fetches XAUUSD hourly history, derives nine price and indicator features, simulates crossover trades, and labels…