Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
2,013 documents
The document describes a QSTrader backtest framework for comparing monthly rebalanced ETF portfolios. Each month, the strategy liquidates holdings and reallocates account equity to target weights. The examples include a 60/40 US stock and bond mix, a…
The article defines a 60/40 benchmark as a portfolio holding 60% equities and 40% bonds, with periodic rebalancing to restore the target weights. It explains the rationale: stock and bond returns may diversify one another, potentially reducing volatility and…
This introduction describes tactical asset allocation as a long-horizon portfolio approach that adjusts broad asset-class exposures at relatively infrequent intervals. It contrasts the approach with fixed buy-and-hold allocations and short-term trading, and…
The document demonstrates a systematic monthly rebalancing strategy using SPY for US equities and AGG for investment-grade bonds. It invests 60% and 40% of initial capital, respectively, at the first month end after the backtest begins. At each later month…
This article examines whether groups of trading-strategy parameter sets selected on historical data continue to perform in a later forward period. It treats the main optimization interval as in-sample and the reserved interval as out-of-sample, then compares…
The article adapts ideas from Molformer, a transformer framework for molecular graphs, to represent financial data. Its proposed market representation combines nodes for individual assets with nodes for recurring multi-asset patterns, aiming to encode…
This article shows how MetaTrader 5’s standard chart-object classes can be extended to display changing textual information on a chart. It explains the class hierarchy from a general object with list and serialization methods, through chart objects that…
The article presents two behavioral software design patterns through MQL5 examples. Memento stores an object's state as a snapshot so it can later be restored, while keeping the object's internal state behind a limited interface. The article notes potential…
The article explains how MQL5 preprocessor definitions can replace symbolic operators and syntax with more word-like forms, making code easier for beginners and other programmers to read. It illustrates definitions for equality, inequality, and logical…
The article presents Temporal Query Network (TQNet), a neural architecture for forecasting multiple related time series. Its attention layer forms queries from trainable vectors that are shifted periodically through time, while keys and values come from the…
The article explains how correlations among open positions change total portfolio risk. It distinguishes instrument-specific risk, which diversification can reduce, from shared systematic exposure, which remains when positions respond to the same market…
This article describes a multi-symbol Expert Advisor that checks market execution conditions before acting on a liquidity-sweep continuation signal. Its filters monitor spread expansion, tick velocity, quote gaps, short-term volatility, slippage estimates,…
This article explains how to extend an MQL5 library so an indicator can retrieve and display price data for selected symbols and timeframes. It reorganizes shared data definitions, adds arrays for chosen symbols and periods, and describes a separate…
This article presents the practical architecture and training of StockFormer, a hybrid trading framework combining predictive coding with reinforcement learning. Its three predictive branches model relationships among assets and forecast market behavior at…
This article describes interface additions to an MQL5 correlation matrix dashboard, which computes Pearson, Spearman, and Kendall relationships across selected symbols, timeframes, and bar windows. Users can drag or minimize the panel, switch between…
This article develops a MetaTrader 5 library method for displaying standard indicator data from another symbol and timeframe in a custom indicator subwindow. It focuses on single-drawn-buffer indicators and changes to the library’s buffer collection and…
This installment outlines an architecture for two-way communication between MetaTrader 5 and spreadsheet software. It contrasts one-way Excel data links such as RTD or DDE with socket-based communication, which can transfer information in both directions.…
This article describes extending a multi-currency Expert Advisor optimization workflow so strategy instances can be grouped using their behavior in a forward period. It contrasts selecting the strongest optimization performers with selecting instances whose…
This article introduces HiSSD, a framework for learning transferable behavior in cooperative multi-agent reinforcement learning. It divides behavior into shared skills that generalize across tasks and task-specific skills that adapt actions to a particular…
This article describes an MQL5 application for visualizing combined trading results across multiple symbols. It modifies the standard MACD Sample expert advisor to test a list of instruments, records deal history after a test, and reads that data to draw a…
This article describes extending an MQL5 trading administration interface with an Analytics Panel. Its two proposed pie charts summarize winning versus losing trades and trade categories, including Forex, stocks, and futures. The panel is populated from…
The article explains how to build an anchored volume profile indicator in MQL5 that displays current-timeframe activity on the main chart and a selected higher-timeframe profile in a separate window. A draggable anchor sets the start of the analysis range,…
The article describes extending a Python-based MetaTrader 5 strategy tester to handle data for multiple instruments and timeframes. It introduces a history manager that fetches bars or ticks for a set of symbols, stores historical data locally, and supports…
This article outlines a pipeline for exporting custom backtest and optimization data from MetaTrader 5 to CSV, then using Python libraries to examine results beyond the platform’s standard reports. Its proposed normalized dataset includes instrument and…