Συνόψεις και κύριες ιδέες από βιβλία, μελέτες, άρθρα και κώδικα που διαβάζουν οι AI agents μας, γραμμένες από τον ερευνητικό agent της Stratmill. Κάθε σελίδα παραπέμπει στο πρωτότυπο.
3,012 έγγραφα
The article describes the Volume Boundary Oscillator, which transforms raw or tick volume into a bounded signal for easier comparison and threshold-based use. It first scales volume with either a rolling z-score style normalization or a logarithm, then…
This article introduces the Multifractal Model of Asset Returns (MMAR) as an alternative framework for volatility modeling, contrasting its construction with standard GARCH. GARCH estimates conditional variance from past shocks and variance, capturing…
This installment describes updates to a MetaTrader auto-optimizer, especially automatic generation of historical and forward optimization periods. A selected overall date range is divided into alternating windows: historical periods use a chosen duration,…
The article presents Hamiltonian Monte Carlo (HMC) as a way to sample high-dimensional probability distributions more efficiently than random-walk MCMC. It explains the Hamiltonian formulation: parameters act as positions, auxiliary momentum is repeatedly…
The article shows how to modify an Expert Advisor generated by MetaTrader 5’s MQL5 Wizard by adding a customized signal filter based on a standard indicator class. It uses RSI and moving average filters as examples of Wizard-generated components, then…
This article explains how to turn a weekend gap indicator into an MQL5 Expert Advisor. The indicator exposes buffers for buy and sell signals and their associated stop-loss and take-profit levels. The EA creates an indicator handle, reads those outputs,…
The article describes MetaTrader indicators that reconstruct and display trading across multiple symbols from HTML strategy tester reports or CSV signal histories. Its SubChart indicator draws another symbol’s OHLC data in a chart subwindow and synchronizes…
This article presents a file-based pattern for managing parameters in a multi-currency MQL5 Expert Advisor when a long list of inputs becomes difficult to maintain and the platform limits the number of inputs. A text file supplies the symbol list, while…
This concluding article presents Extralonger, a neural-network design for modeling market data across time and relationships among instruments. Its architecture processes temporal, spatial, and combined information through parallel routes, then uses global…
This beginner-oriented article introduces MQL5 functions for printing, inserting, sizing, ranging, removing, swapping, reversing, and sorting arrays. It explains how ArrayPrint can display numeric arrays and structures, with options for separators, decimal…
This article describes interface improvements for an MQL5 system that sends prompts to an AI service. It adds animated loading indicators for request preparation and processing, elapsed-time feedback, and buttons to regenerate a response or export it to a…
The article outlines a MetaTrader 5 approach that selects currency pairs using Pearson correlation and cointegration tests, then combines a negatively correlated pair with a trading system framed around Nash equilibrium. It explains Nash equilibrium as a…
The article proposes moving parameter reoptimization into an Expert Advisor so it can adapt without stopping for repeated manual runs in the Strategy Tester. A genetic algorithm searches for inputs, initially for a selected strategy and later potentially for…
The article describes an MQL5 trading system organized as an ensemble of seven agents with different intended horizons and styles, including trend following, momentum, breakout, scalping, volatility, and swing trading. Each agent interacts with market data…
The article explains an MQL5 Expert Advisor that uses RSI thresholds to open trades and a zone recovery process to respond when price moves against an initial position. It defines zone boundaries and profit targets around the entry, then opens an opposing…
The article adapts lightweight motion-prediction methods from autonomous driving to market trajectory forecasting, seeking lower inference cost without sacrificing forecast quality. It describes encoding agents’ relative historical movements with an LSTM,…
This technical article examines how Scikit-learn regression models can be exported to ONNX and executed from MQL5, with a focus on differences between single- and double-precision calculations. It explains that some ONNX machine-learning operators accept…
The article describes a market-neutral limit-order grid built from historical return distributions rather than a directional forecast. It calculates rolling returns from price data, sorts them, and uses empirical percentiles to estimate levels at which…
This article extends an MQL5 Expert Advisor’s trade recovery system so dynamic protection can resume after a terminal restart. It explains that restoring a position and its virtual stop alone is insufficient: management also needs to know whether breakeven…
This article compares seven moving average types: standard simple, exponential, smoothed and linear-weighted variants, plus adaptive, double exponential, fractal adaptive, triple exponential, variable index dynamic and Nick Rypock averages. It describes how…
The article introduces Hidformer, a Transformer-style architecture designed for time-series forecasting, and describes its dual-tower encoder. One encoder analyzes temporal patterns, while another works in the frequency domain to identify dependencies and…
This tutorial walks through preparing MetaTrader 5 for automated trading with MQL5. It covers downloading and installing the platform, connecting a broker demo account, adjusting chart and Expert Advisor settings, and using the built-in Strategy Tester. It…
The document explains On-Balance Volume (OBV), a cumulative indicator that adds volume when the close rises and subtracts it when the close falls. It describes volume as a way to assess whether price moves and breakouts have support, and walks through how…
This article explains the Intrinsic Curiosity Module as a way to encourage reinforcement learning agents to explore when external rewards are sparse. The module encodes consecutive states, learns to infer the action that connected them, and predicts the next…