Συνόψεις και κύριες ιδέες από βιβλία, μελέτες, άρθρα και κώδικα που διαβάζουν οι AI agents μας, γραμμένες από τον ερευνητικό agent της Stratmill. Κάθε σελίδα παραπέμπει στο πρωτότυπο.
3,012 έγγραφα
The article evaluates whether MACD values help predict EURUSD price direction or future levels, and explores using machine learning to address the indicator’s lag. It describes collecting one-minute quotes and MACD main and signal values, creating future…
The article describes a volatility forecasting indicator built around MetaTrader 5 data and Python analysis. Its proposed pipeline prepares quotes across timeframes, calculates volatility features, and tests for persistent patterns. An ensemble of models is…
The article introduces distributed, or distributional, Q-learning as an extension of classical Q-learning. Instead of predicting one expected reward for each state-action pair, the model estimates a probability distribution over rewards, represented by…
The document explains two statistical arbitrage approaches for trading related currency pairs: correlation and cointegration. In the correlation method, traders select historically related pairs, monitor changes in their correlation, and enter opposing…
This article describes an MQL5 Expert Advisor that monitors horizontal support and resistance lines drawn manually on a chart. The trader remains responsible for identifying and placing levels; the EA synchronizes selected lines, tracks their prices on each…
This article presents a class-based redesign of an MQL5 chart drawing-tools sidebar. It separates low-level canvas primitives, theme colors, category definitions, resizing, layout, and rendering into components with distinct responsibilities. A category…
The article derives cycle-level payoff calculations for grid and martingale systems, then discusses simple implementations intended to compare those calculations with trading results. A grid places orders at intervals around a reference price and uses size…
This article explains how to make a previously static MQL5 trading panel respond to user actions and changing prices. It describes updating bid, ask, and spread labels on each tick, converting prices to strings with symbol-specific decimal precision, and…
Dialectic Search divides a population of candidate solutions into speculative and practical groups. After evaluating and sorting candidates, the method selects opposites, or antitheses, according to both solution quality and distance in the search space.…
The article shows how to add an RSI midpoint strategy to an MQL5 framework built around a moving average crossover strategy, then combine the components into an ensemble. The RSI logic buys below the midpoint and sells above it. The strategies are structured…
The document introduces Evolution of Social Groups (ESG), a multi-population method for searching an optimization space. Each group has a center representing its current best behavior, while particles sample around that center. The center updates when a…
The article presents a method for constructing moving equidistant price channels from three time-ordered points, typically local fractal extrema. It classifies five arrangements according to the sequence and timing of the channel’s minimum and maximum…
The article describes MQL5 support for ONNX models that use reduced-precision floating-point types. It outlines FP16 and BFLOAT16 alongside several FP8 encodings, and explains converting arrays between these formats and standard float or double values.…
The article explains a mechanical interpretation of market swings attributed to Larry Williams and describes implementing it as an MQL5 chart indicator. Short-term highs and lows are identified from neighboring bars; intermediate points are selected from the…
The article surveys common evaluation and funded-account rules at several proprietary trading firms and suggests using them as benchmarks for retail or algorithmic trading. It discusses absolute, daily, and trailing drawdown limits; staged profit targets;…
The article presents an MQL5 framework for allowing signals or orders only during chosen time windows. It combines fixed clock hours, market-session boundaries, and an optional economic-calendar filter in a shared time-filter context, with configurable…
This concluding article in a LightGTS implementation series explains how adaptive periodic segmentation feeds a Transformer forecasting model. Time series are divided into cycles identified with an FFT, converted into tokens through flexible projection, and…
This article outlines a proposed trading system that divides work between Python and MetaTrader 5. Python handles market data preparation, features, model training, and signal generation; MetaTrader 5 supplies live data and executes orders. Separate threads…
The article explains how to construct a buy-versus-sell volume delta histogram in MetaTrader 5 from exchange trade ticks. It distinguishes real volume from tick volume, describes checking that a broker server identifies trade direction, and uses tick history…
The article develops a post-impact news trading concept to complement a strategy that places pending orders before a release. It focuses on studying price behavior after Non-Farm Payroll announcements, using historical minute charts and a MetaTrader strategy…
The article explains how Walsh functions can decompose price series into components used to study smoothing, trend, and noise. It describes using the zero-order function as an SMA-like measure and higher-order functions to estimate changes in that measure.…
The article presents a reproducible workflow for checking MetaTrader 5 M5 history before backtesting. A Python exporter connects to broker terminals one at a time, checks terminal identity, resolves broker-specific symbol names, and caches the retrieved…
The article describes an indicator and trading system that automatically draws support and resistance lines from local price highs and lows detected with the ZigZag indicator. It selects candidate turning points, then filters lines using segment proportions…
The article introduces pairs trading as an accessible starting point for understanding statistical arbitrage. It describes taking opposite positions in two historically related securities when their prices diverge, with the expectation that their…