Aleksey / Notícias
Возможно ты попал по адресу! ))
Объявление простое.
Есть наработки в области [парного] кросс-трейдинга.
Последняя реализация ТС на С# для крипты. Надёжна и проста как "Теория всего."
Не ясна пока доходность, т.к. тестера не имеется.
Много граблей посчитано, шишки получены, достигнута определённая ясность сознания.
Могу поделиться опытом со страждущими!)
А так же идеями...
Взамен - взаимность, участие, энтузиазм, интерес к предмету.
Так же, в листе ожидания зависла задачка для программиста среднего уровня. Просто нет на это времени.
Задачка не очень сложная, но ставящая точку в представлении о доходности существующей ТС (кросс-трейдинг).
и вносящая ясность по её адаптации для форекс. Что потребует сосредоточенности и понимания mql-специфики.
Кому интересно, кликните Алексея в тг-группе: https://t.me/kulibyatino
и пообщаемся.
#кросс_трейдинг #парный_трейдинг
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
GOLD CatBoost Angle MA 3 ST V1 EA works on the Catboost algorithm. The technology described in my articles is used, which you can read below: Experiments with neural networks (Part 1): Revisiting geometry https://www.mql5.com/en/articles/11077 Experiments with neural networks (Part 2): Smart neural network optimization https://www.mql5.com/en/articles/11186 Experiments with neural networks (Part 3): Practical application https://www.mql5.com/en/articles/11949
![Nikolay Moskalev Nikolay Moskalev](https://c.mql5.com/avatar/2014/8/53EA0245-C4F5.jpg)
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
GOLD CatBoost Distans MA 3 ST V1 EA works on the Catboost algorithm. The technology described in my articles is used, which you can read below: Experiments with neural networks (Part 1): Revisiting geometry https://www.mql5.com/en/articles/11077 Experiments with neural networks (Part 2): Smart neural network optimization https://www.mql5.com/en/articles/11186 Experiments with neural networks (Part 3): Practical application
![Реter Konow](https://c.mql5.com/avatar/avatar_na2.png)
![](https://c.mql5.com/6/952/splash-758425.png)
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
CatBoost Angle MA 3 ST V1 EA works on the Catboost algorithm. The technology described in my articles is used, which you can read below: Experiments with neural networks (Part 1): Revisiting geometry https://www.mql5.com/en/articles/11077 Experiments with neural networks (Part 2): Smart neural network optimization https://www.mql5.com/en/articles/11186 Experiments with neural networks (Part 3): Practical application https://www.mql5.com/en/articles/11949 Experiments with
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
CatBoost Distans MA 3 ST V1 EA works on the Catboost algorithm. The technology described in my articles is used, which you can read below: Experiments with neural networks (Part 1): Revisiting geometry https://www.mql5.com/en/articles/11077 Experiments with neural networks (Part 2): Smart neural network optimization https://www.mql5.com/en/articles/11186 Experiments with neural networks (Part 3): Practical application https://www.mql5.com/en/articles/11949
![Nikolay Moskalev Nikolay Moskalev](https://c.mql5.com/avatar/2014/8/53EA0245-C4F5.jpg)
![Реter Konow](https://c.mql5.com/avatar/avatar_na2.png)
![Maxim Dmitrievsky](https://c.mql5.com/avatar/2024/3/66034e17-bb79.jpg)
https://www.mql5.com/ru/channels/machinelearning
![Maxim Dmitrievsky](https://c.mql5.com/avatar/2024/3/66034e17-bb79.jpg)
![Time series clustering in causal inference](https://c.mql5.com/2/74/Time_series_clustering_in_causal_inference___LOGO.png)
Clustering algorithms in machine learning are important unsupervised learning algorithms that can divide the original data into groups with similar observations. By using these groups, you can analyze the market for a specific cluster, search for the most stable clusters using new data, and make causal inferences. The article proposes an original method for time series clustering in Python.
![Maxim Dmitrievsky](https://c.mql5.com/avatar/2024/3/66034e17-bb79.jpg)
![O escore de propensão na inferência causalidade](https://c.mql5.com/2/72/Propensity_score_in_causal_inference____LOGO.png)
O artigo examina o tema de pareamento na inferência causal. O pareamento é utilizado para comparar observações semelhantes em um conjunto de dados. Isso é necessário para determinar corretamente os efeitos causais e eliminar o viés. O autor explica como isso ajuda na construção de sistemas de negociação baseados em aprendizado de máquina, que se tornam mais estáveis em novos dados nos quais não foram treinados. O escore de propensão desempenha um papel central e é amplamente utilizado na inferência causal.
![Maxim Dmitrievsky](https://c.mql5.com/avatar/2024/3/66034e17-bb79.jpg)
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
![Оптимизация и тестирование торговых стратегий (Часть 1): Взгляд на "Red Dragon H4", "BOLT", "YinYang", и "Statistics SAR"](https://c.mql5.com/2/70/Optimizing_and_Testing_Trading_Strategies_Part_1____LOGO.png)
Так как я постоянно занимаюсь, разработкой разного рода торговых систем сегодня хочу поделиться с Вами несколькими из них по стратегиям "Red Dragon H4", "BOLT", "YinYang" и "Statistics SAR". Данные стратегии были найдены на просторах интернета.
![Roman Poshtar](https://c.mql5.com/avatar/2019/12/5DE4DBC6-D492.jpg)
![Maxim Dmitrievsky](https://c.mql5.com/avatar/2024/3/66034e17-bb79.jpg)
![Inferência causal em problemas de classificação de séries temporais](https://c.mql5.com/2/66/Causal_inference_in_time_series_classification_problems___LOGO.png)
Neste artigo, examinaremos a teoria da inferência causal usando aprendizado de máquina, bem como a implementação de uma abordagem personalizada em Python. A inferência causal e o pensamento causal têm suas raízes na filosofia e psicologia e desempenham um papel importante na nossa compreensão da realidade.
![Ireneusz Pacek](https://c.mql5.com/avatar/2021/6/60BD3BB0-EC59.png)