Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,012 dokumenttia
This article introduces K-nearest neighbors as a non-parametric method for classification and regression, then walks through a classifier implemented in MQL5. For a new observation, the method calculates its Euclidean distance from labeled examples, selects…
This programming tutorial explains how a fixed-size ring buffer can support efficient calculations on streaming market data. A conventional moving-average implementation rescans the full window whenever a new observation arrives, so its work grows with the…
The article uses Monte Carlo simulations to examine how per-trade risk affects growth, drawdowns, and the ability to withstand losing streaks. It compares synthetic systems with different win rates and reward-to-risk ratios, all presented as having positive…
This tutorial extends an earlier risk-management tool by adding functions to estimate maximum volume from free margin, adjust lot size to a per-trade risk limit, and derive a stop-loss distance from a selected risk and lot. It also explains MQL5 chart…
This article compares a EURGBP daily moving-average crossover system with an AI-assisted version. The baseline combines exponential moving averages, a stochastic oscillator, and ATR-based exits. The proposed method trains models on earlier data to estimate…
The article introduces Mamba, a selective state space model architecture, as an approach to processing long financial time series with linear sequence-length scaling. It explains the hidden-state formulation, input-dependent selection of information, and…
This article explains how to estimate a market’s dominant cycle and use it to adapt technical indicators. It represents a cycle as a complex signal with in-phase and quadrature components, derives those components with a truncated Hilbert transform, and…
This installment explains how a MetaTrader 5 position-view indicator can work with an Expert Advisor, Chart Trade, and a mouse interaction indicator. The EA manages when the position indicator is added or removed, while the indicator remains a separate…
The article presents NRTR, a dynamic channel indicator that signals when closing prices cross a trailing level set from recent highs or lows. Its lookback period grows as a trend develops and resets after a reversal, so earlier prices are excluded from the…
This article walks through a feed-forward neural network in MQL, from the weighted sums and biases of individual neurons to a network with two hidden layers. It uses hyperbolic tangent activations in the hidden layers and softmax outputs for three trading…
This article explains the Square of 9 as a spiral arrangement of numbers used to project possible price levels and time cycles. It describes the square’s construction, the role of angular and numerical relationships, and the use of price transformations and…
This article introduces dimensionality reduction as a way to manage large, correlated sets of trading indicators. It presents truncated singular value decomposition (SVD), which projects centered data onto a smaller number of components, and non-negative…
The document examines the tension between non-stationary price levels, which retain historical information, and integer differencing, which can discard that memory. It introduces long-range dependence and fractional differentiation as a way to seek…
This article describes a hand-built candlestick pattern recognizer split between MQL5 and Python. The proposed system extracts open, high, low, and close data, applies geometric rules to candles, and labels formations such as hammers, shooting stars,…
The document explains an automated approach to the Quasimodo reversal pattern. It identifies a sequence of confirmed swing pivots: a shoulder, a pullback leg, a more extreme head, and a break through the leg that signals a possible reversal. The program…
The document introduces Recurrence Quantification Analysis (RQA) as a way to measure repeated patterns in time series. It explains time-delay embedding, distance calculations between reconstructed states, and thresholding those distances to form a recurrence…
The document describes a custom MQL5 indicator for marking confirmed smash day reversal patterns. A bullish setup begins when a bar closes below the lows of a selected number of earlier bars without being an outside bar; confirmation occurs when price rises…
The document explains the Dream Optimization Algorithm (DOA), a population-based method that could be used to tune trading-system parameters. It divides candidate solutions into groups with different numbers of dimensions to modify. During exploration, group…
This article describes a cross-market trend-following method that combines each market’s own momentum with momentum from markets that tend to lead it. It first scales price changes by estimated volatility, then forms moving-average crossover oscillators at…
The article presents ACEFormer, a neural architecture for forecasting financial time series, especially noisy and irregular high-frequency data. Its pipeline first smooths inputs with convolutional filters, then applies an adaptive ensemble empirical mode…
This article explains how a MetaTrader 5 trade request moves from the terminal to the server, becomes an order, and may produce deals that change positions. It distinguishes request validation from execution: a successful basic check or an accepted request…
This beginner guide walks through building a C++ dynamic library in Visual Studio 2017 and connecting it to MetaTrader. It covers project setup, Unicode configuration, copying the build output into the terminal’s library folder, and exporting functions with…
This article describes an MQL5 program that connects to an AI chat service and presents a multi-turn conversation in a scrollable chart-based interface. The interface design includes timestamps, conversation history, scrollbar display modes, mouse-wheel…
This MQL5 cookbook installment adapts an existing Expert Advisor to use a selectable indicator as part of its position-opening conditions. The example offers a Moving Average, Commodity Channel Index, or custom price-channel indicator. It explains how to…