Yevgeniy Koshtenko / 个人资料

Разбирается практическое применение L1 Trend Filter для очистки шума и формирования структурных признаков, совместимых с live-торговлей. Показан полный цикл: H1-данные 29 инструментов из MetaTrader 5, каузальная фильтрация, CatBoost на горизонте трёх L1-баров, честный walk-forward и распределение лотов по VaR. Читатель получает воспроизводимый кодовый конвейер и методику портфельной оценки.

Статья продолжает серию об AI Hedge Fund и снимает три ограничения v4: репутации аналитиков теперь персистентны в SQLite, EA выведен из критического пути исполнения, а сигналы совета пятнадцати рассылаются на несколько брокеров через TradeMux REST API. Логика совета и риск-менеджмента не менялась: Python получает данные через MetaTrader 5 SDK и исполняет ордера напрямую. Результат — устойчивость к перезапускам и масштабирование на несколько терминалов.

В статье разобрана архитектура советника на клеточном автомате с 10 000 адаптирующихся параметров и независимым бинарным предиктором на горизонте 10 баров. Показано трёхуровневое онлайн-обучение, эволюция стратегий и валидация через кольцевой буфер и матрицу ошибок. Параметры входа сведены к Magic Number, торговые настройки вычисляются из ATR и пяти геномов. Тест EURUSD H1 дал ориентировочный Hit Rate около 58% против ~51% у фиксированной MLP.

Описана архитектура, в которой MQL5-советник выполняет только сбор данных и исполнение, а логика вынесена в Python-сервер с тремя агентами LangChain: сигнальным, новостным и риск-менеджером. Агенты последовательно обрабатывают запрос по WebSocket, при отказе любого возвращается hold. Решения и фактический PnL сохраняются в SQLite, формируя память и статистику. Читатель получит схему взаимодействия, протокол команд и подход к обратной связи.

Метапромптинг — подход, при котором LLM сама оптимизирует торговые инструкции на основе реального P&L и метрик качества сигналов. В статье показана практическая реализация на Python и MQL5: реестр версий промптов, исполнительный агент, оценщик по directional accuracy и profit factor и мета-LLM, которая в цикле генерирует улучшения. Решение встраивается в советник без остановки торговли.

The article presents a regression-based approach to forecasting Renko bars using CatBoost: the model estimates the logarithmic return of the next bar and the uncertainty of the forecast. We will examine a cascade of residual models with OOF validation using TimeSeriesSplit, shrinkage, and overall early stopping, as well as conditional bias correction. On EURUSD D1, a reduction in OOF-MAE was achieved, along with approximately 65% directional accuracy. A working script for MetaTrader 5 is provided that generates a signal, position size, SL, and TP in brick units.

The article examines the architecture of a committee consisting of 15 AI agents: ten analysts and four risk officers vote in three parallel phases, and the Chair records the final result. Isolated pair contexts with separate reputations are used for eight currency pairs. The dynamic vote threshold depends on the daily PnL targets. The Expert Advisor uses only the signal, SL and TP, which allows for evaluation pf the quality of its decisions without any additional mechanics.

The article discusses the projection of EURUSD daily candlesticks onto the secp256k1 elliptic curve and the extraction of 96 features (EC+TA) to predict the direction of the next candlestick in CatBoost. The price mapping to the curve and the training pipeline on 2,000 D1 bars are shown; the full model achieves a test AUC of 0.6508, with EC features contributing 60.6%. The materials are suitable for reproduction in Python/MetaTrader 5.

An LLM agent with SQL memory in MetaTrader 5 — an architecture that eliminates the main limitation of traditional LLM Expert Advisors (EAs): the loss of context between queries. Each agent decision is recorded in SQLite along with the market conditions at the time of the signal — RSI, MA alignment, volatility — and after the position is closed, the outcome is written to the database. When the next request comes in, the agent reviews its own history — similar past RSI conditions and the last three agent decisions — and only then analyzes the current market. The result is a system that remembers its errors between restarts and adapts its behavior based on accumulated statistics, rather than starting from scratch with each new bar.

The article describes the architecture of a trading system consisting of 20 Grok (xAI)-based LLM agents, each of which embodies a unique trading philosophy — from pure momentum to a statistical z-score. The system applies a genetic algorithm directly during trading: every 20 trades, it automatically eliminates weak agents, clones strong ones with a prompt mutation, and publishes a leaderboard on the MetaTrader 5 chart — without interrupting trading and without using any SDK.

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.

The article describes the architecture of a multi-agent trading system based on the grok-4-fast language model, in which, instead of a single system prompt, four independent analysts with fundamentally different roles operate: a bull, a bear, a risk manager, and an arbiter. Three analysts run in parallel using a ThreadPoolExecutor and, within 3–5 seconds, formulate well-reasoned positions based on the same market data; after that, a deterministic judge renders a final verdict according to strict rules.

The article describes a competitive architecture for MetaTrader 5 in which ten LLM agents, each with different trading rules, manage their own capital and open independent positions using unique magic numbers. The system prompt and the agent's trading aggressiveness are adjusted based on PnL results and the trade streak. A reproducible framework with operating modes and monitored metrics is presented, suitable for testing and further optimization.

The article examines three key obstacles to integrating LLMs with MetaTrader 5: the lack of direct access, strict rate limits, and API key security given the architectural limitations of MQL5. A configuration is proposed that uses a local Python server as a bridge between the Expert Advisor and OpenRouter. The article covers WebSocket and fallback to TCP, storing the key on the server, batch processing of multiple symbols, and constructing a technical prompt. Readers get a ready-made architecture that reduces latency and costs.