
The SpikingBrain framework demonstrates a unique approach to data processing: neurons respond only to significant events, effectively filtering out noise. Its event-driven architecture reduces computational costs while preserving key information about price movements. Adaptive thresholds and the ability to use pre-trained modules ensure the model's flexibility and scalability.

We implement a Time Series Shapelet library for MQL5 that finds the subsequence of price history whose z-normalized shape best separates two labels and derives the decision threshold from information gain. Because candidate searches on prices always return a winner, the fit includes a purged hold-out and a calibrated block permutation null. You get a reusable facade and rules you can plot and evaluate against an explicit noise floor.

We use the MetaTrader 5 AI Assistant to execute the full workflow end to end: create an EA from a natural‑language prompt, compile it, break and watch it self‑correct from compiler output, backtest it, and compare a controlled re‑run. The article details the underlying MCP extensions, configuration and safety limits, and how to connect external AI clients. Readers get a repeatable process for building and testing EAs inside the platform.

The article presents an MQL5 script that reads closed deals, groups them by date, and renders a calendar grid for daily P&L and trade count. It explains the data model, normalization to midnight, robust week/weekday mapping, diverging and single-hue color scales, and CCanvas-based drawing, plus a verification script and weekday summary. This helps you quickly locate clusters and quiet periods and cross-check findings with logged totals.

We are developing and implementing the Flock by Leader algorithm in MQL5: sub-flocks are formed based on the ARF metric, and the leader is determined by the highest personal best rather than by the centroid's position. We present the update formulas for the swarm roles and the separation mechanism. The C_AO_FBL class is compatible with the test bench and has been tested on the Hilly, Forest, and Megacity functions with dimensionalities from 10 to 1000 coordinates, which simplifies reproduction and comparison.

Learn how Smart Trendline Manager separates creation from lifecycle control while handling both manual and auto-generated trendlines. It demonstrates discovery, registration, proximity and touch handling, bounce/break confirmation, post-break resurrection, expiration, and state-driven visualization. This gives you a consistent, configurable way to manage multiple lines through one orchestrated update process.

MACD signal-line crossovers often reflect range noise rather than true momentum shifts, producing whipsaws. We apply a two-layer meta-labeling pipeline with an Optuna-optimized regime gate to filter entries on EURUSD H1, turning a gross-losing rule into a positive but not statistically significant track. A secondary Random Forest adds no lift due to too few gated samples, clarifying when filtering helps and when the ML layer is data-starved.

This article presents an MQL5 script that extracts closed trade history, computes empirical win rate and payoff, and evaluates consecutive-loss probabilities using the geometric tail, plus risk of ruin from edge and position size. It plots a CCanvas ruin curve with a live marker at the chosen risk and prints a probability summary, including the account's worst historical streak in theoretical context.

How to purchase a trading robot from the MetaTrader Market and to install it?
A product from the MetaTrader Market can be purchased on the MQL5.com website or straight from the MetaTrader 4 and MetaTrader 5 trading platforms. Choose a desired product that suits your trading style, pay for it using your preferred payment method, and activate the product.
How to Test a Trading Robot Before Buying
Buying a trading robot on MQL5 Market has a distinct benefit over all other similar options - an automated system offered can be thoroughly tested directly in the MetaTrader 5 terminal. Before buying, an Expert Advisor can and should be carefully run in all unfavorable modes in the built-in Strategy Tester to get a complete grasp of the system.

A Sharpe ratio read off the best of many optimization runs is not the number it looks like. This article ships a reusable native CDeflatedSharpe class that turns a raw Sharpe into an honest confidence statement. The Probabilistic Sharpe Ratio corrects it for sample length and for skew and kurtosis; the Deflated Sharpe Ratio adds the correction almost nobody applies, for the number of variants you tried before keeping the best. Everything is from scratch, the sample moments, the normal CDF and its inverse included, so there is no Python, no DLL and no library. On a real sweep of 56 moving-average variants on XAUUSD the winner looked significant at 98.5 percent by PSR, then fell to 90.6 percent once the 56 trials were admitted, below the usual bar. That gap is the selection bias, made measurable.

This article implements an MQL5 Expert Advisor that scores each impulse leg behind a swing extreme with a 0–100 Candle Imbalance Score. The score combines four bounded components—body dominance, directional consistency, leg efficiency, and Fair Value Gap coverage—to filter weak swings before any pullback setup is armed. You will see enforced swing alternation, a state machine for first-clean-retest-only entries, and a three-mode trailing stop, enabling consistent setup selection and exit management.

The article provides a detailed examination of the integration of the ST-Expert framework's approaches into the Extralonger architecture, which enables the simultaneous analysis of temporal and spatial representations of data. The results of testing on real historical data are presented, demonstrating the model's effectiveness and its robustness to market anomalies. The article describes the framework's modular structure, which ensures reproducibility, flexibility for research, and the ability to optimize components in stages.

This article presents a practical debugging workflow with MetaEditor's integrated AI Assistant and a comparison to the previous external approach. We fix a controlled set of syntax and API errors in a D1 PriceMarker EA, inspect modifications, and recompile. The result is validated in the Strategy Tester, with clear boundaries between compilation success and required runtime checks.

The article presents a session analysis workflow in MQL5 that standardizes sessions as structured data with timing, OHLC, range, net move, and the sequence of extremes. It measures how range builds at 25%, 50%, 75%, and 100% of session duration. The chart shows session markers, a compact comparison panel, and an interactive inspector to review individual occurrences.

The article describes the transition from four-voice debates to the Council of Fifteen: ten analysts, four independent risk managers, and a Chair, with strict voting rules. It examines the roles of the participants, the three-phase architecture, and the parallel execution of a full cycle in 10–15 seconds. It shows the operational log, the risk-gate rules, and backward compatibility so you can quickly connect the system to an Expert Advisor.

Many traders know what they want to analyze or automate but cannot navigate MetaTrader 5, use MetaEditor, or translate an idea into working MQL5 code. This article shows how the AI Assistant and MCP turn one natural-language prompt into a complete workflow: strategy development, editing, debugging, chart interaction, testing, and permission-controlled trading. We apply the process by building MCP_Accessibility_Assistant.mq5, leaving you with a working, accessible EA and a reusable prompt-driven development method.

In this article, we will examine how to build and apply Markov chains in market conditions: from selecting states and counting transitions to generating forecasts of trajectories and levels. We will also see how Markov chains can be applied to qualitative and quantitative data, ways to account for rare events, and the impact of the forecast horizon. Examples are provided using prices and indicators, as well as an option for evaluating a sequence of trades, with ready-to-use implementations in MQL5.

This article describes an MQL5 Expert Advisor that models the market as a random graph rather than a fixed structure. Bars are encoded into discrete states; bar-to-bar moves form a decaying, Laplace-smoothed transition matrix, and a k-step random walk yields a bounded directional signal gated by an Erdos–Renyi null-model test. A separate trade-outcome graph over R-milestones learns survival probabilities to manage exits, turning position management into evidence-based rules.

This MQL5 dashboard aggregates closed deals by symbol and UTC hour, calculates win rate and average reward‑to‑risk, and displays the results as two color‑coded heatmaps. A companion table in the Experts tab highlights the strongest and weakest symbol/hour cells, with an option to require a minimum trade count to reduce noise.

In this article, we continue implementing the ST-Expert framework approaches, focusing on the practical aspects of applying them using MQL5. Earlier, we examined the theoretical foundations and key components of the model; now we move on to working directly with graph attention algorithms and local and global attention distribution. The main goal of this work is to demonstrate how ST-Expert's conceptual ideas are transformed into workable solutions for analyzing and forecasting financial time series.

The article extracts the series' divergence logic into DivergenceEngine.mqh, a reusable header for MQL5 indicators and Expert Advisors. It details the struct-based design, oscillator options (MPO4 or RSI), pivot and state handling, and the minimal access API. A Parabolic SAR EA demonstrates integration by adapting the acceleration factor from the detected divergence, providing a clear pattern you can reuse without duplicating code.

The series develops state persistence for MQL5 Expert Advisors. Part 1 delivers a crash-safe key-value store: a CStateStore class that saves through a temporary file and a rename, carries a versioned header with a checksum, and stores integers, doubles, strings, booleans, and double arrays, plus a demo advisor that resumes a counter and a rolling window after a restart. Readers get a compact include file and a pattern that protects the live state file if the process dies mid-save.