สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article presents a probabilistic framework for combining technical indicator signals. It treats a profitable entry as the outcome of interest and estimates each indicator’s historical hit rate, then uses a naive Bayes formulation to estimate the…
The article introduces monoids as sets equipped with a closed, associative binary operation and an identity element, then applies the idea to trading choices. Example decision sets include lookback length, chart timeframe, applied price, indicator, and…
This article explains quantization as mapping continuous or finely measured feature values into a smaller set of discrete levels. It describes how a histogram can help inspect a feature’s distribution and how cutoffs define bins, with values then encoded by…
The article describes an MQL5 Expert Advisor that automates selected Wyckoff accumulation and distribution sequences. It uses a finite state machine to enforce event order: identify a range after a directional move, detect a spring or upthrust, confirm with…
This programming tutorial surveys MQL5 strings and their uses in trading software. It explains declaration and initialization, including the distinction between a null uninitialized value and an empty string, and covers concatenation with operators and…
This installment of a MetaTrader replay-system series addresses showing the time remaining until the next bar. The author first documents a platform problem: changing a chart timeframe during replay can cause the platform to lose contact with ticks or bars…
The article explains nonlinear transformations for financial time series and develops indicators based on order statistics. It contrasts logarithmic transformations, which turn arithmetic operations into geometric ones, with methods that sort observations to…
The article explains Central Force Optimization (CFO), a population-based numerical optimization method inspired by gravitational motion. It initializes candidate probes in a bounded search space and assigns their objective values as masses. Better-scoring…
The article presents nonlinear time-series tools for examining financial-market structure. It explains estimating fractal dimension with a box-counting procedure: cover a price series at several scales, count the required boxes, and fit a line to the…
The article explains how to integrate an Optuna Bayesian hyperparameter search into an existing machine-learning training pipeline while retaining a scikit-learn search path. In the Optuna path, model parameters, sample-weight scheme, decay, and linearity…
This article offers practical guidance for traders commissioning an automated trading program. It recommends validating the strategy before hiring a programmer, testing it across multiple historical intervals, and treating the implementation task separately…
The article presents a probability-based framework for evaluating automated trading ideas, using gaps as its example. It models a single-asset Expert Advisor through position, price, and equity changes, then simplifies the analysis by representing activity…
This installment in a MetaTrader replay and simulation series describes how a chart indicator can trigger a request to close a displayed position. The indicator cannot alter positions on the trading server directly; an Expert Advisor must receive its event…
The document explains MR Swing, a swing-trading system that uses volatility-adjusted Value Charts to identify pullbacks and different rules for bull and bear regimes. Value Charts compare prices with a moving fair-value baseline and scale the difference by…
The article describes a workflow for adding a machine-learning model to an existing MQL5 order block strategy that also uses Fibonacci analysis. It begins by translating the strategy into Python so its pattern detection, indicators, order handling, and risk…
The article describes a bridge that mirrors open MetaTrader 5 positions in MetaTrader 4. Its core premise is that matching the instrument and position volume is enough to reproduce aggregate position profit, even if the individual MT4 orders are closed in a…
This article explains particle swarm optimization (PSO) as a population search method. Each candidate solution has a position and velocity; its movement reflects its own best-known position and the best position found by the swarm, with random factors and an…
The article turns point and figure chart patterns into automated trend trades. It outlines entries around prior column highs and lows or breaks of support and resistance, with stop placement at chart pivots or trend lines. Position size is calculated from…
The article explains the Group Method of Data Handling (GMDH), focusing on its multilayer iterative algorithm (MIA), and describes an MQL5 implementation for building polynomial prediction models. MIA pairs input variables to create candidate partial models,…
This article offers a workflow for maintaining MQL5 projects across development and trading terminals. It recommends keeping each project's experts, scripts, libraries, and data in separate directories, and using a shared project location to avoid…
The article describes extending an MQL5 binomial distribution viewer with a DirectX-rendered 3D mode. Histogram bars show simulated frequencies, while a projected theoretical probability mass function (PMF) helps compare observed samples with expected…
The article builds on earlier neural-network trading experiments and describes testing small feedforward networks inside MetaTrader 5. It compares three input approaches, including candle-size information, price-shape measurements, and moving-average slope…
The article explains how bid and ask prices affect market-order entries and exits, then presents a MetaTrader 5 indicator approach for measuring historical spreads from tick data. It compares observed average spreads with broker-declared levels and…
The article describes a MetaTrader 5 workflow for collecting balance and equity data from Expert Advisor optimization passes, calculating several custom criteria, and displaying selected results as graphs and screenshots. It divides the implementation…