Olamide Daniel Adebayo / 个人资料

This article implements a PSI-based drift watchdog for MQL5 EAs. It compares a feature and the model's predicted probability against a quantile-based reference using a rolling window at a configurable cadence, applies hysteresis to avoid flapping, and raises a webhook on state transitions. You get tested math, an audit CSV and a plotting indicator, plus tuning guidance for thresholds, window size, and cooldown.

The article builds an MQL5‑native weak‑labeling engine that infers per‑indicator trust from vote agreement, then fuses five noisy signals into P(Buy) using Expectation‑Maximization. We describe the EA architecture, rolling‑window refits, abstain handling, diagnostics, and a majority‑vote baseline used for comparison. Readers can reuse the EM library, swap in their own labeling functions, and obtain a transparent, probability‑based entry filter.

This article builds an uncertainty-based routing layer for an EA: an online logistic regression scores P(up), Shannon entropy measures uncertainty, and a streaming P² quantile enforces a fixed review budget. Signals auto-trade, auto-skip or go to a human checkpoint, replaced by proxy modes in the Strategy Tester. It is judged on a held-out window against a trade-everything baseline, matched-frequency and seeded controls, and an exact profit split. No edge is claimed.

The article focuses on label-auditing for meta-labeling, not on a new entry signal. It presents a native MQL5 implementation of confident learning with out-of-fold scoring and calibrated pruning, plus an EA switch that trains the meta-filter on raw or cleaned datasets. A controlled Strategy Tester comparison helps you quantify noise and choose a pruning level that preserves generalization.

This article benchmarks one MLP forward pass implemented three ways in MQL5: native code, ALGLIB, and ONNX Runtime. We quantify numerical fidelity versus a float64 ground truth and execution latency (mean/percentiles), then outline practical criteria and a ready‑to‑use harness to help you choose and integrate the right engine in an EA.

The article guides you through building a real‑time Hilbert Spectrum indicator in MQL5: EMD produces IMFs, a discrete FIR Hilbert transform yields analytical signals, and a CCanvas renderer draws a time–frequency–energy heatmap. Implementation details include extrema detection, SD stopping, phase unwrapping, Nyquist clipping, and bin accumulation. Use the panel to identify active cycle bands and regime shifts while keeping trade rules separate.

This article presents a native MQL5 Fractional Fourier indicator for measuring whether the dominant cycle is speeding up or slowing down. It searches for the rotation that maximizes spectral concentration in a detrended analytic window, using a unitary eigenvector FrFT and a golden‑section entropy search, and reconstructs a band‑limited cycle line. Results on known chirps and on real closes across symbols/timeframes show where the method is reliable, its bias, and its limited forward information in practice.

The article shows how to compare two trading forecasters in MQL5 using the Diebold–Mariano test with HAC‑corrected variance and the Harvey–Leybourne–Newbold adjustment. It explains implementation details, including loss choices, horizon‑dependent lag windows, rolling computation, verdict handling, and a manifest‑driven configuration, plus a Student‑t implementation without external libraries. An EA and an indicator provide a live dashboard and significance bands for practical, defensible model selection.

This article defines a Protocol Buffers contract for the MetaTrader 5-Python boundary and implements a length-prefixed Protobuf-over-TCP client in MQL5, since MQL5 cannot speak real gRPC natively. A small Python shim relays those frames to a genuine grpc.aio server, unary today, with streaming already live on the backend. You get schema-enforced, strongly-typed messages, explicit errors, retry/backoff, and a Strategy Tester cache for reproducible backtests where sockets don't run.

This article implements a lightweight feature-space drift guard in MQL5 using 1D Wasserstein‑1: sort-and-pair scoring on equal windows, IQR normalization per feature, and gating via both a weighted composite and a max-statistic. Configuration comes from a JSON manifest (window sizes, weights, warn/critical thresholds, actions). It runs next to an ONNX classifier and is validated with Strategy Tester results and explicit caveats.

Sample correlation matrices can look precise yet be mostly noise. This article implements a dependency-free RMT cleaner in MQL5: Jacobi eigendecomposition, Marchenko–Pastur eigenvalue screening, and average-noise reconstruction that preserves the matrix trace and unit diagonal. It explains integration into a basket EA so the denoised matrix improves stability of hedge ratios and weights between rebalances, while keeping the code portable and auditable.

A step-by-step guide to a native Isolation Forest in MQL5 focused on execution metrics rather than price. It details five features, tree construction and path‑length scoring, rolling‑window training, CSV logging, and FILE_COMMON persistence, all integrated into OnTradeTransaction(). The resulting circuit breaker flags unusual fills in real time and applies controlled responses to stabilize live trading under changing execution conditions.

The article details a native MQL5 Kafka producer that speaks the wire protocol over raw TCP. It implements RecordBatch v2 encoding, varints, and CRC32C, and adds batching, acks, and retry logic, all without a sidecar or DLL. Use it to publish JSON-structured trading signals from a single terminal to Kafka, where dashboards and other services subscribe independently.