Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,012 dokumenttia
This overview describes MetaTrader 5 features for market analysis, order handling, programming, and automated-strategy evaluation. Charting coverage includes multiple display styles and timeframes, technical indicators, drawing tools, event-calendar data,…
This article plans the structure and setup flow for a MetaTrader 5 application that helps discretionary traders scan signals across selected markets. Its initial setup has three stages: choose symbols from Market Watch, select timeframes, and define trading…
The article demonstrates a one-step-ahead EURUSD H1 forecasting workflow using EViews for econometric modeling and an MQL4 Expert Advisor to evaluate forecasts. It examines quote distributions and autocorrelation, applies unit-root testing, and uses a…
The article describes the Bat Algorithm, a population-based heuristic that models search agents as bats adjusting their positions through frequency, velocity, pulse rate, and loudness. It outlines initialization, movement, local search around the current…
The article explains how the updated MQL5 Wizard builds Expert Advisors from reusable signal, trailing, and money management modules. Its main change is a hierarchical signal system: each signal can combine forecasts from up to 64 advisor signals, including…
This article explains Wolfe Waves as wedge-like price patterns used to identify a possible entry direction, a projected price target, and an estimated time to reach that target. In the buy example, successive swing points define two lines: a later…
This article surveys and implements market microstructure features for machine learning. Its OHLCV path estimates spreads and price impact using measures such as Roll, Corwin–Schultz, Amihud, and Hasbrouck. A separate path uses raw ticks to calculate per-bar…
This article adapts survival analysis to trade duration, asking how the chance of reaching a target changes for positions that remain open as they age. It represents each trade by duration, outcome, and strategy identifier, then uses Kaplan–Meier survival…
This article explains how to reduce the chart objects required to display a Market Profile indicator. Instead of drawing each histogram segment as a separate rectangle, it uses the CCanvas class to render the profile for each day on a bitmap object. A…
The article explains how to combine numerical predictions from multiple trained models, with MQL5 implementations of several ensemble methods. It begins with a simple average, whose squared error is bounded by the average squared error of the component…
The article starts with a manual hourly trading strategy built from ADX, the Relative Vigor Index, and the Accelerator Oscillator. It specifies directional entry conditions requiring agreement among all three indicators, then uses fixed position size,…
The article replaces a moving-average component in an earlier feedback-control trading design with a supervised statistical model of EUR/USD. It outlines a workflow that gathers daily OHLC data, labels future prices at a defined horizon, compares candidate…
The article explains Thomas DeMark’s rules for identifying price extremes and drawing trend lines with less discretionary interpretation. A TD high is a candle whose high exceeds the highs of a chosen number of candles on both sides; a TD low uses the…
The article presents an Optuna workflow for tuning financial machine learning models while preserving a financial data contract. It describes Bayesian parameter search with a TPE sampler, fold-by-fold evaluation using PurgedKFold, separate fitting and…
The article describes an automated reporting workflow that connects a MetaTrader 5 Expert Advisor with a Python report processor. The EA exports dated trading history to CSV and launches the Python script; the processor calculates trading analytics, creates…
The article proposes SEAL, an experimental process for adapting a trading language model from trade outcomes. It stores predictions and results as training examples, assigns each example a weight based on factors such as directional correctness, model…
The article outlines a modular trading robot that uses Python for analysis and MQL5 for execution. A central MarketMaker component coordinates modules for volume analysis, arbitrage, economic conditions, and risk control. The proposed architecture runs…
The article describes a reinforcement learning setup for trading that adds a Director to the usual Actor–Critic pair. The Actor selects actions, the Critic estimates their reward quality, and the Director classifies whether actions fit the learned strategy.…
The article outlines a foreign-exchange arbitrage prototype that uses Python with MetaTrader 5. It retrieves tick data for multiple currency pairs, removes duplicate timestamps, calculates synthetic prices from combinations of quoted pairs, and compares…
This installment describes a MetaTrader 5 interface for selecting and editing position price levels in a market replay or simulation tool. It uses a highlighted horizontal line and nearby controls to make a level easier to select when several lines are close…
The article explains cross-recurrence quantification analysis (CRQA), a nonlinear way to compare the evolving states of two time series. Each series is embedded separately using matching dimension and delay settings; pairwise distances between embedded…
This installment describes the decoder and autoregressive prediction half of a native MQL5 implementation of Kronos, a transformer model for financial candles. It reconstructs normalized OHLCVA bars from hierarchical tokens, embeds token pairs alongside…
The article shows how to create mountain, iceberg, and colored line displays in MetaTrader 5 with a custom MQL5 indicator. It describes using price data in one indicator buffer and a second buffer to control filling or mark a threshold. In outline mode, a…
This tutorial explains how to preserve Expert Advisor settings across restarts and share them among MetaTrader terminals on the same computer. Its method is to group related, fixed-size values such as numeric trading parameters in a simple MQL5 structure,…