Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,012 dokumenttia
The article explains how to search for slower lead/follower behavior between related assets, where one instrument’s returns may precede another’s by minutes or longer. It frames the setup as a potential mean-reversion opportunity for cointegrated assets and…
The article introduces the Fisher Transform as a way to reshape normalized market-cycle values whose distribution may concentrate near cycle extremes rather than follow a Gaussian pattern. It describes normalizing prices over a rolling range before applying…
The article describes a feedback mechanism that adjusts an Expert Advisor’s trade volume according to the slope of its balance curve. Before a prospective trade, the system estimates slope from recent closed trades; when the slope weakens, it reduces volume,…
This technical overview explains how activation functions map neural network inputs to outputs and why their derivatives matter for backpropagation. It presents formulas and MQL5 usage examples for functions including ELU, exponential, GELU, sigmoid, tanh,…
The article presents Wolfe Waves as reversal patterns formed by five turning points around a narrowing or parallel price channel. It describes projecting possible points with Fibonacci retracements and extensions, drawing trend lines through the pivots, and…
This article explains an Expert Advisor that visualizes the Asia, Tokyo, London, and New York trading sessions on a MetaTrader 5 chart. It uses broker-server time to draw session ranges and display each session’s open, high, low, and close. On-chart controls…
The article describes an MQL5 entry signal that encodes each of the last 64 bars as a binary value: bullish bars set a bit, while other bars leave it unset. A perceptron then adds the weights for active bits to a bias to produce an activation score. The…
This article introduces classifier ensembles and explains bagging, or bootstrap aggregation, as a parallel method for reducing prediction variance. Each base classifier is trained on a bootstrap sample, and their outputs are combined through averaging or…
This article demonstrates how to create a MetaTrader indicator that colors candles and marks inside bars. It defines an inside bar as one whose high and low remain within the preceding bar’s range, while noting that some traders use broader definitions. A…
This article explains convolutional neural networks as a way to recognize patterns in price-chart data. It describes how convolution filters scan input sequences to produce feature maps, while subsampling retains local maxima or averages to reduce…
This article completes a trading-oriented implementation of RefMask3D, a language-guided 3D point-cloud segmentation framework. It focuses on the Object Cluster Module, which combines two self-attention blocks, an intervening cross-attention block, and a…
The article introduces indicator emissions: plotted points at intersections between indicator lines, intended as a visual way to study recurring shapes and their possible relationship to price movement. Its example combines an exponential moving average with…
The article builds a MetaTrader 5 chart tool that aggregates option gamma by strike to display a signed gamma exposure profile. It describes calculating Black-Scholes gamma, weighting contracts by open interest, and deriving call and put walls from the…
This article extends a MetaTrader 5 Expert Advisor interface for editing pending orders and position levels on a chart. Its central change is to let mouse movement update a local preview rather than send every intermediate price adjustment to the trade…
The document describes an automated strategy that treats a moving average crossover as an initial directional signal, then requires further price action before placing an order. A finite-state process tracks the setup through crossover detection, momentum…
This article explains the difference between automatically created MQL5 objects and objects created dynamically through pointers. It demonstrates that using an uninitialized object pointer can terminate a program, then shows how CheckPointer can detect an…
The article introduces APIs and the MQL5 WebRequest function through a project connecting MetaTrader 5 to Telegram. It explains how HTTP requests carry actions to an external service, and describes request methods, endpoints, headers, message bodies, and…
This article demonstrates how to bring a public MQL5 library into an Expert Advisor project using MQL5 Algo Forge and Git. Its example connects the SmartATR indicator repository to a Simple Candles project, with the goal of checking that the library can be…
The article outlines a custom MQL5 trailing module that uses a Bloom filter to screen repeated prices and a recurrent neural network (RNN) state to moderate stop adjustments. Price values are converted to point-based integers, hashed into a compact bit…
Explore, Discover and Learn (EDL) is an unsupervised skill-learning method for hierarchical reinforcement learning. It addresses limited state coverage in approaches that train skills from a prior distribution. EDL first gathers a broad sample of environment…
The Code Lock Algorithm (CLA) is a population-based optimization method that encodes each candidate parameter as a sequence of decimal digits. Digit sequences map to values within each parameter’s search range. Candidate solutions are modified by copying…
This experiment adds features from a fixed three-qubit circuit to a bidirectional LSTM that predicts the next EURUSD hourly candle’s direction. Recent-window mean return, volatility, and range determine rotation angles; linked qubits produce an eight-outcome…
The Artificial Tribe Algorithm (ATA) is a population-based optimization method inspired by tribal behavior. It represents candidate solutions as individuals with personal best positions and a shared best position. The method switches between two search…
This article describes an experimental machine-learning system for forecasting movement across eight currency pairs on a 15-minute timeframe. It combines four groups of inputs: 3D-bar features derived from price, time, volume, and volatility; a quantum…