Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
3,012 dokumenti
The article examines how common technical-analysis representations affect the information a trader sees. It explains that a simple moving average has a delay tied to its smoothing period. Shifting the plotted values can compensate for that delay, but leaves…
This article extends a graphical-object library so programs can identify property-change events and retain an object's earlier names. It proposes storing the current name alongside prior names in a dynamic property array, allowing the library to display…
The article presents methods for estimating basic distribution characteristics from a finite sample, with time-series analysis as the motivating use. It discusses the influence of outliers and describes a center estimate built by sorting five measures: the…
This article outlines a workflow for adapting a pretrained language model to produce outputs aligned with a trading strategy, with foreign exchange pairs as the intended application. It explains why fine-tuning can be useful after general pretraining and…
The article explains Parabolic SAR as a trend-following tool primarily used to set trailing stops. It outlines rising and falling calculations using the prior SAR, an extreme point (the trend’s high or low), and an acceleration factor that increases when new…
The article builds a reusable Z-score calculation class for an MQL5 indicator and Expert Advisor. The score measures a closing price’s distance from a rolling simple moving average in units of the rolling standard deviation over the same lookback. Its…
This installment explains implementation details of the Community of Scientists Optimization algorithm, a population-based method for searching an objective function. Its fund allocation routine reserves a share of available resources for new outsiders and…
This article presents a reusable averaging function for MetaTrader indicators and Expert Advisors. Its SmoothXSeries interface selects among nine smoothing methods, including adaptive or specialized algorithms as well as simple, exponential, smoothed, and…
This installment of a MetaTrader library series moves shared event tracking into a base object and connects the account object to that framework. Descendant objects can reuse methods for setting monitored property thresholds, reading current values and…
This article combines Bill Williams’ Alligator, Awesome Oscillator, and Fractals into trend-following entry and exit rules. It then describes adding an ADX filter for trend strength, ATR-based stops, and neural-network forecasts. The indicator rules use…
This article explains how to build configurable feedforward neural networks in MQL5 using matrix operations instead of hard-coded layer calculations. It represents each layer’s computation as an input–weight product plus a bias, and describes allocating…
This article presents a strategy concept for forecasting GBP/USD with conventional market features and alternative macroeconomic data from the Federal Reserve Bank of St. Louis FRED database. The proposed inputs include a British sterling overnight-market…
This article describes integrating a Time-MoE architecture into an Actor–Director–Critic trading system. It outlines a SwiGLU embedding, a sparse Mixture of Experts layer with a Top-K router and shared expert, and an attention module that combines a recent…
This article outlines a pipeline for training a reinforcement-learning trading model on hourly XAUUSD data and deploying its predictions in MetaTrader 5. It describes retrieving historical bars, cleaning and preparing the data, creating return and…
This article describes a retail Expert Advisor that trades relationships among three currency pairs using a grid of pending orders. It frames the method as an alternative to capturing fleeting triangular arbitrage: instead of waiting for a perfect pricing…
This article extends a higher-timeframe candlestick trend constraint indicator by adding MetaTrader 5 moving averages and the Relative Strength Index. Its main filter compares a short smoothed moving average with a much slower simple moving average, using…
This article explains how to check a covariance matrix eigendecomposition using the spectral theorem. For a real symmetric covariance matrix, multiplying the eigenvector matrix by the diagonal eigenvalue matrix and the transpose of the eigenvector matrix…
This article introduces chemical reaction optimization (CRO), a population-based metaheuristic inspired by molecular reactions and energy conservation. Candidate solutions are treated as molecules, with objective-function values represented through potential…
This article presents a modular approach to detecting geometric structures in price data, focusing on triangles and rectangles. It motivates automation as a way to replace manually drawn chart objects with repeatable rules, using swing highs and lows as…
The article describes “liquid charts,” which rebuild bars on a chosen trading timeframe from smaller-period price data. By shifting the bar boundaries, the method produces alternate views of price action that can reveal different candle shapes and patterns.…
The document presents an inverse fair value gap strategy for an MQL5 expert advisor. A fair value gap is defined as a three-candle imbalance; the inverse setup looks for price to revisit the latest gap and pass through it rather than react as expected. That…
The article turns Bill Williams’ five-bar fractals into rule-based trading patterns for an MQL5 expert advisor. It describes repeated fractal lows or highs as possible support or resistance, a close beyond a prior fractal as a breakout, compressed swing…
The document introduces sparse attention as a way to reduce the computation and memory demands of transformer self-attention, whose pairwise sequence comparisons grow quadratically with sequence length. It outlines standard query, key, and value…
The document explains how to build an MQL5 heatmap that summarizes average bar returns by weekday and hour. It defines each bar’s percentage return from consecutive closes, excludes weekend bars, and aggregates observations into a five-by-twenty-four grid.…