Muhammad Minhas Qamar
Muhammad Minhas Qamar
  • 정보
no
경험
2
제품
15
데모 버전
1
작업
0
거래 신호
0
구독자
Developer by Profession, Trader by Hobby

Gmail: ayanminhasshayar@gmail.com
Muhammad Minhas Qamar
게재된 기고글 Foundation Models for Trading (Part II): Decoding, Autoregression, and an Exact KV-Cache
Foundation Models for Trading (Part II): Decoding, Autoregression, and an Exact KV-Cache

We complete the native MQL5 port of Kronos: the decoder, the predictor's decode_s1 and decode_s2 stages with their cross-attention traps, and the autoregressive loop that produces a multi-bar forecast. Then we profile and make it roughly 4.5x faster with an exact KV-cache and pre-transposed weights, verifying every stage against PyTorch.

Muhammad Minhas Qamar
게재된 기고글 Bloch's Relative Moving Average (RMA) Framework Implementation In MQL5
Bloch's Relative Moving Average (RMA) Framework Implementation In MQL5

We port Daniel Bloch's Relative Moving Average framework into a complete MetaTrader 5 system. Instead of smoothing price, the RMA measures where price sits inside its own recent distribution on a [0,1] fractile scale, and drives four cross-strategies with a regime-adaptive exit. Includes the engine, indicators, and a backtested Expert Advisor.

Muhammad Minhas Qamar
게재된 기고글 Implementing and Benchmarking Bag-of-SFA-Symbols (BOSS) Against Dynamic Time Warping (DTW)
Implementing and Benchmarking Bag-of-SFA-Symbols (BOSS) Against Dynamic Time Warping (DTW)

This article implements BOSS from scratch in MQL5 and applies it to regime classification: SFA turns windows into words, bags record word frequencies, and an ensemble over window lengths votes on labels. We cover the encoding steps, the BOSS distance, training with auto-generated regime labels, and practical parameters. A BTCUSD benchmark versus DTW shows higher macro accuracy on clean data and markedly faster inference.

Muhammad Minhas Qamar
게재된 기고글 Porting the Canonical Catch22 Time-Series Feature Set and Testing It on Volatility Regimes
Porting the Canonical Catch22 Time-Series Feature Set and Testing It on Volatility Regimes

We present a native MQL5 implementation of the catch22 feature set: all 22 canonical time-series characteristics in a reusable class validated against pycatch22. Using a leak-free pipeline (chronological split, purging, embargo), we run a three-arm ablation—classic indicators, catch22, and combined—for volatility-regime classification. Finally, we deploy the combined model as a Strategy Tester regime filter to quantify its impact on a simple baseline strategy.

1
Muhammad Minhas Qamar
게재된 기고글 Bayesian Online Change-Point Detection (BOCPD) in MQL5: One Regime-Break Signal, Three Ways to Use It
Bayesian Online Change-Point Detection (BOCPD) in MQL5: One Regime-Break Signal, Three Ways to Use It

This article delivers Bayesian Online Change-Point Detection as a single, dependency-free MQL5 class that maintains a per-bar, causal probability of a regime break. We use it three ways: a live monitor, a moving average that flushes on breaks, and a risk overlay with a matched-frequency random control. Readers get a reusable primitive to watch structural change, adapt indicators, and gate exposure after detected shifts.

1
Muhammad Minhas Qamar
게재된 코드 EVT Crash Gauge
시장의 잠재적인 폭락 및 급등 가능성을 파악하기 위해 MQL5로 이식된 극값 이론(EVT).
Muhammad Minhas Qamar
게재된 코드 SAX Forecaster
기호적 집계 근사법(SAX)을 기반으로 한 예측 모델
Muhammad Minhas Qamar
게재된 코드 Relative Moving Average EA
블로흐(Bloch)의 상대 이동평균(Relative Moving Average) 프레임워크에 포함된 네 가지 크로스 전략 모두를 MQL5로 구현한 것으로, 변동성 구간에 따른 그의 ‘적응형 크로스오버 청산(Adaptive Crossover Exit)’ 전환 규칙이 적용되어 있습니다. 진입 및 청산은 프랙틸 공간에서 이루어지므로, 모든 종목에서 임계값의 의미가 동일합니다.
Muhammad Minhas Qamar
게재된 코드 Relative Moving Average Indicator
Daniel Bloch의 ‘Relative Moving Average’ 프레임워크를 MQL5로 충실하게 이식한 버전입니다. 이 프레임워크는 현재 종가를 해당 윈도우 내 분포에서 [0, 1] 척도로 순위를 매기며, 이는 종목 간 비교가 가능합니다. 또한, 분位수, 체제 분류 및 방향성 일관성을 가독성 높은 버퍼 형태로 출력합니다.
Muhammad Minhas Qamar
게재된 기고글 Symbolic Aggregate Approximation (SAX) in MQL5: Historical Analog Search and Forecasting
Symbolic Aggregate Approximation (SAX) in MQL5: Historical Analog Search and Forecasting

Symbolic Aggregate approXimation (SAX) encodes price windows as short words to enable fast, sound similarity search on history. We implement SAX in pure MQL5, including Gaussian breakpoints, PAA, and the lower-bounding MINDIST, and validate it with a test harness. An indicator applies a no-lookahead, two-stage search, summarizes forward paths in ATR units, and draws a forecast fan, explicitly indicating when the sample shows no edge.

1
Muhammad Minhas Qamar
게재된 기고글 Ordinal Pattern Transition Networks in MQL5
Ordinal Pattern Transition Networks in MQL5

We implement ordinal pattern transition networks in MQL5: a Lehmer-code encoder, a directed network over ordinal price patterns, and three complexity metrics. Two indicators expose a trend-versus-range regime from time-irreversibility and an efficiency gauge from permutation entropy, with a transparent parameter sweep showing how to tune settings on FX data.

Muhammad Minhas Qamar
게재된 기고글 Mapping Dealer Gamma Exposure (GEX) in MetaTrader 5: Walls, the Zero-Gamma Flip, and a Chart Overlay
Mapping Dealer Gamma Exposure (GEX) in MetaTrader 5: Walls, the Zero-Gamma Flip, and a Chart Overlay

In this article we build a dealer gamma-exposure map in MQL5. From an option chain, the tool computes per-strike GEX, finds the call and put walls, and solves for the zero-gamma flip that separates a mean-reverting regime from a trending one, then draws it all on the chart. CSV and native-symbol data paths included.

Muhammad Minhas Qamar
게재된 기고글 Foundation Models for Trading (Part I): Porting Kronos to Native MQL5
Foundation Models for Trading (Part I): Porting Kronos to Native MQL5

Kronos is a pretrained transformer that models OHLCV bars the way a language model predicts words. We reimplement its tokenizer/encoder and transformer block in native MQL5, export weights to flat .bin files, and remove Python from runtime entirely. Part 1 delivers preprocessing and BSQ tokenization plus a bit-for-bit verification harness against PyTorch, so you can run the encoder inside MetaTrader 5 with confidence.

Muhammad Minhas Qamar
게재된 기고글 From Option Chain to 3D Volatility Surface in MetaTrader 5
From Option Chain to 3D Volatility Surface in MetaTrader 5

This article walks through creating an MT5 indicator that ingests option chains from native symbols or CSV, inverts prices to implied volatility via a hybrid Newton–Raphson/bisection method, and assembles a clean strike–expiry grid. It then renders a shaded, rotatable 3D surface with the platform's DirectX layer, enabling clear, in-terminal analysis of skew and term structure using live or file-based data.

Muhammad Minhas Qamar
게재된 기고글 Beyond GARCH (Part VIII): The MMAR Library And Putting it to Work in an Expert Advisor
Beyond GARCH (Part VIII): The MMAR Library And Putting it to Work in an Expert Advisor

This article finalizes the MMAR project with a CMMAR facade class and a demo Expert Advisor for MetaTrader 5. The facade exposes a compact API—configure, Fit(), Forecast()—that wraps partition analysis, spectrum fitting and Monte Carlo simulation. You will learn how to load data, fit the model and obtain a volatility forecast, with diagnostics and status handling for robust use in EAs.

Muhammad Minhas Qamar
게재된 기고글 Extreme Value Theory in MQL5: Building a Tail-Risk Crash Gauge Beyond Monte Carlo VaR
Extreme Value Theory in MQL5: Building a Tail-Risk Crash Gauge Beyond Monte Carlo VaR

Standard MQL5 risk tools read risk from recent history and miss how heavy the downside tail can be. We implement Extreme Value Theory in MetaTrader 5: a Peaks‑Over‑Threshold fit of the Generalized Pareto Distribution via ALGLIB, a live indicator that reports EVT VaR/ES and tail shape, and an EA that sizes positions from the tail estimate. A controlled backtest illustrates reduced drawdown for unchanged entries.

Muhammad Minhas Qamar
게재된 기고글 How to Connect AI Agents to MQL5 Algo Forge via MCP
How to Connect AI Agents to MQL5 Algo Forge via MCP

This article extends Part 1 by giving an AI access to the development lifecycle on MQL5 Algo Forge. We implement an MCP server over the Forgejo REST API so an agent can create repositories, commit Expert Advisors, branch from main, open pull requests, file issues, and tag releases. You will get a ready-to-run Python server, clear tools, and a safer, reversible workflow.

Muhammad Minhas Qamar
게재된 기고글 Beyond GARCH (Part VII): Monte Carlo Volatility Forecasting in MQL5
Beyond GARCH (Part VII): Monte Carlo Volatility Forecasting in MQL5

We implement the CMonteCarlo module that turns the fitted MMAR parameters into a volatility forecast via Monte Carlo. It runs N independent simulations over a chosen horizon and reports mean, median, standard deviation, and a percentile-based 95% confidence interval, with access to per-run values if needed. Adaptive cascade depth selects the minimal k such that b^k covers the horizon, keeping the run fast and consistent.

Muhammad Minhas Qamar
게재된 기고글 Beyond GARCH (Part VI): Fractional Brownian Motion And The Multiplicative Cascade in MQL5
Beyond GARCH (Part VI): Fractional Brownian Motion And The Multiplicative Cascade in MQL5

This article implements the MMAR Simulation Engine that turns fitted parameters (H, distribution, coefficients, sample volatility) into synthetic price paths. It builds multifractal trading time via a multiplicative cascade, synthesizes fractional Brownian motion with Davies–Harte or Cholesky, scales it to target volatility, and composes the process by time deformation. Readers get a reusable MQL5 class, method choices by path length, and validation steps for scenario testing and Monte Carlo use in the next part.

Muhammad Minhas Qamar
게재된 기고글 Beyond GARCH (Part V): Fitting the Multifractal Spectrum in MQL5
Beyond GARCH (Part V): Fitting the Multifractal Spectrum in MQL5

This article builds the Spectrum Fitter: from tau(q) we compute f(alpha) with a discrete Legendre transform, then fit Normal, Binomial, Poisson, and Gamma spectra under box constraints using BLEIC. The best model by SSE is selected, and its parameters (eg, alpha min, alpha max or alpha_0, gamma) become the cascade inputs for multifractal simulation.

3
123