Yevgeniy Koshtenko
Yevgeniy Koshtenko
3.6 (8)
  • Bilgiler
2 yıl
deneyim
13
ürünler
37
demo sürümleri
1
işler
0
sinyaller
0
aboneler
Qualified Investor of Kazakhstan and the Russian Federation.
Trading since 2016, algorithmic trading since 2019, machine learning and programming since 2021.

I develop expert advisors, trading robots, indicators, smart contracts, cryptocurrency token and coin codebases, business automation software, and turnkey AI models.

Currently working on an institutional-grade trading system for my own hedge fund and on my own AI blockchain.
Author of 100+ international articles published in different languages worldwide.
Yevgeniy Koshtenko
"CFTC Data Mining in Python and Building an AI Model" makalesini yayınladı
CFTC Data Mining in Python and Building an AI Model

Let's try mining CFTC data, downloading COT and TFF reports via Python, connecting all this with MetaTrader 5 quotes and an AI model, and get forecasts. What are COT reports in the Forex market? How to use COT and TFF reports for forecasting?

3
Yevgeniy Koshtenko
"Mining Central Bank Balance Sheet Data to Get a Picture of Global Liquidity" makalesini yayınladı
Mining Central Bank Balance Sheet Data to Get a Picture of Global Liquidity

Mining central bank balance sheet data provides a picture of global liquidity in the Forex market and key currencies. We combine data from the Fed, ECB, BOJ and PBoC into a composite index and use machine learning to uncover hidden patterns. This approach turns raw data into real trading signals by combining fundamental and technical analysis.

3
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Лучший торговый робот мира - мой! В итоге сейчас в Мидасе 11 прогнозирующих нейросетей, как регрессионных так и классификационных, плюс отдельная мета - надсистема, одна 12-я нейросеть которая обучается на матрице из всех признаков, всех выходов и ошибок всех моделей. В надсистеме анализируется матрица из 5000 столбцов и 100 000 строк данных, всего размерность датасета 500 000 000 единиц данных..

Есть много разных модулей: и анализ трендов, и анализ объёмов, и анализ реальных объёмов валютных фьючерсов и опционов Чикаго, и анализ позиций хэдж-фондов, и анализ балансов и трендов балансов мировых центробанков включая ЕЦБ и ФРС, и анализ более 2500 экономических показателей от Евростата, Насдаг Стата и Всемирного банка, хоть как-то влияющих на курс валют. Есть и компьютерное зрение, и использование квантового суперкомпьютера IBM, даже модули анализирующие цены через последовательности Фибоначчи, через нумерологический скор, и через астрологические циклы, это не шутка)

Плюс отдельный модуль, составляющий оптимальный портфель по всём сигналам.

Целевая прибыль должна увеличиться с прошлых 1000 пунктов в день, как минимум до 1200-1300 пунктов в сутки.

35000 строк кода. Это лучший робот мира. Midas!
Yevgeniy Koshtenko
"CAPM Model Indicator for the Forex Market" makalesini yayınladı
CAPM Model Indicator for the Forex Market

Adaptation of the classical CAPM model for the Forex currency market in MQL5. The indicator calculates expected return and risk premium based on historical volatility. The indicators rise at peaks and bottoms, reflecting the fundamental principles of pricing. Practical application for counter-trend and trend-following strategies, taking into account the dynamics of the risk-reward ratio in real time. The article includes mathematical apparatus and technical implementation.

1
Yevgeniy Koshtenko
"ARIMA Forecasting Indicator in MQL5" makalesini yayınladı
ARIMA Forecasting Indicator in MQL5

In this article we are implementing ARIMA forecasting indicator in MQL5. It examines how the ARIMA model generates forecasts, its applicability to the Forex market and the stock market in general. It also explains what AR autoregression is, how autoregressive models are used for forecasting, and how the autoregression mechanism works.

3
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Долгосрочный портфель по модулю Мидаса по портфельной теории + своп фактору. Каждый день капает своп.
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Сегодня минус -0,16%
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Сигналы Мидаса на сегодня. Горизонт прогноза - плюс минус 24 часовых бара. Распределение лотов по портфельной теории Марковица)
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Чистая доходность вчерашних сигналов Мидаса +1,1% без плеча. Или около 1000 пунктов (10 000 пипсов). Можете проверить сами)
Yevgeniy Koshtenko ürün yayınladı

ARIMA Neural Link - Trading Revolution When Mathematics Meets Artificial Intelligence Tired of unpredictable losses? Fed up with guessing market movements like reading tea leaves? While you're losing money on emotional decisions, professional traders are already using tomorrow's technology. Introducing ARIMA Neural Link The world's first hybrid indicator combining the power of classical ARIMA modeling with cutting-edge neural network algorithms. This isn't just another indicator — it's a quantum

Yevgeniy Koshtenko
Yevgeniy Koshtenko
Сигналы на Форекс от 5 модулей Мидаса на понедельник. Тут далеко не все модули - я пересобираю систему.
Yevgeniy Koshtenko
"Self-Learning Expert Advisor with a Neural Network Based on a Markov State-Transition Matrix" makalesini yayınladı
Self-Learning Expert Advisor with a Neural Network Based on a Markov State-Transition Matrix

Self-training EA with a neural network based on a state matrix. We combine Markov chains with a multilayer neural network MLP developed using the ALGLIB MQL5 library. How can Markov chains and neural networks be combined for Forex forecasting?

4
Yevgeniy Koshtenko
"Markov Chain-Based Matrix Forecasting Model" makalesini yayınladı
Markov Chain-Based Matrix Forecasting Model

We are going to create a matrix forecasting model based on a Markov chain. What are Markov chains, and how can we use a Markov chain for Forex trading?

2
Yevgeniy Koshtenko
"Integrating Computer Vision into Trading in MQL5 (Part 2): Extending the Architecture to 2D RGB Image Analysis" makalesini yayınladı
Integrating Computer Vision into Trading in MQL5 (Part 2): Extending the Architecture to 2D RGB Image Analysis

Computer vision for trading: how it works and how to develop it step by step. We create an algorithm for recognition of RGB images of price charts using the attention mechanism and a bidirectional LSTM layer. As a result, we obtain a working model for forecasting the EURUSD price with the accuracy of up to 55% in the validation section.

2
Yevgeniy Koshtenko
Yevgeniy Koshtenko
Ура! Мне дали доступ к базе SEC (Комиссии по ценным бумагам и биржам США).

Теперь мне доступны любые отчёты по всем позициям всех фондов крупнее 100 млн. $.

Это для нового модуля Мидаса.

Следующая статья будет посвящена анализу связей между движениями капитала мировых фондов и изменениями цен на бирже.
Aleksandr Seredin
Aleksandr Seredin 2025.05.12
Круто! Это очень мощная идея. Жду новую статью с нетерпением. )))
Yevgeniy Koshtenko
"Quantitative Analysis of Trends: Collecting Statistics in Python" makalesini yayınladı
Quantitative Analysis of Trends: Collecting Statistics in Python

What is quantitative trend analysis in the Forex market? We collect statistics on trends, their magnitude and distribution across the EURUSD currency pair. How quantitative trend analysis can help you create a profitable trading expert advisor.

2
Yevgeniy Koshtenko
"Forex Arbitrage Trading: A Matrix Trading System for Return to Fair Value with Risk Control" makalesini yayınladı
Forex Arbitrage Trading: A Matrix Trading System for Return to Fair Value with Risk Control

The article contains a detailed description of the cross-rate calculation algorithm, a visualization of the imbalance matrix, and recommendations for optimally setting the MinDiscrepancy and MaxRisk parameters for efficient trading. The system automatically calculates the "fair value" of each currency pair using cross rates, generating buy signals in case of negative deviations and sell signals in case of positive ones.

3
Yevgeniy Koshtenko
"Integrating Computer Vision into Trading in MQL5 (Part 1): Creating Basic Functions" makalesini yayınladı
Integrating Computer Vision into Trading in MQL5 (Part 1): Creating Basic Functions

The EURUSD forecasting system with the use of computer vision and deep learning. Learn how convolutional neural networks can recognize complex price patterns in the foreign exchange market and predict exchange rate movements with up to 54% accuracy. The article shares the methodology for creating an algorithm that uses artificial intelligence technologies for visual analysis of charts instead of traditional technical indicators. The author demonstrates the process of transforming price data into "images", their processing by a neural network, and a unique opportunity to peer into the "consciousness" of AI through activation maps and attention heatmaps. Practical Python code using the MetaTrader 5 library allows readers to reproduce the system and apply it in their own trading.

3
Yevgeniy Koshtenko
"Predicting Renko Bars with CatBoost AI" makalesini yayınladı
Predicting Renko Bars with CatBoost AI

How to use Renko bars with AI? Let's look at Renko trading on Forex with forecast accuracy of up to 59.27%. We will explore the benefits of Renko bars for filtering market noise, learn why volume is more important than price patterns, and how to set the optimal Renko block size for EURUSD. This is a step-by-step guide on integrating CatBoost, Python, and MetaTrader 5 to create your own Renko Forex forecasting system. It is ideal for traders looking to go beyond traditional technical analysis.

3