Danil Sidorov
RU EN DE
Telegram

AI trading bot

An algorithmic trading bot where a PyTorch neural network predicts price moves and generates trading signals

Машинное обучение / Трейдинг

Live interactive demo stand

An exact copy of the project interface and business logic with demo data. All actions run in real time.

Сигналы считаются на потоке данных автоматически, без ручного отслеживания

StackPython, PyTorch, Flask, pandas, NumPy, scikit-learn, ccxt

Safe perimeter (NDA): production logic on test data

What to test in the stand:
  1. Запустите торговый цикл с инференсом ансамбля GRU-нейросетей
  2. Проверьте результаты walk-forward валидации и пороги мета-фильтра
  3. Оцените график накопленного PnL и журнал генерации сигналов
http://127.0.0.1:8080/
Live Stand

Нейро-трейдер

бот: работает брокер: paper (OKX) Эквити: 10 248.50 $ данные: 14:00:00 UTC

Открытые позиции

1 активная
Символ Позиция Объём Вход SL / TP PnL ($) Действие

Последние сигналы модели

порог prob ≥ 0.50, meta ≥ 0.55
Символ Время бара Прогноз Вероятности [D, F, U] Мета-уверенность Решение

Лог торгового цикла

цикл: 60с

                

Журнал сделок (journal.csv)

последние закрытые и открытые ордера
Время Событие Символ Направление Объём Цена SL TP Причина PnL ($) Эквити ($)

Turnkey implementation

Need a similar system for your business processes?

I will develop the architecture, fault-tolerant backend, and fast interface. Protected by NDA, clean transferable code, and transparent milestones.

  1. Free timeline and budget estimate within one day
  2. Contract and invoice
  3. Warranty and post-launch support

On weekdays usually within a couple of hours

I will reply personally, no aggressive sales pitch

Task

The trader wanted to stop watching charts by hand. He needed a system that finds entry points on its own using a trained model. Rigid rules built from a set of indicators did not suit him.

Solution

I trained a PyTorch neural network on historical quotes and built it into a bot that collects data, calculates features, makes predictions and generates signals. Inference is separate from the strategy, so entry and exit logic can change without retraining the model.

What was done

  • Trained a PyTorch neural network on historical quotes
  • Automated data collection, feature calculation and signal generation
  • Separated inference from the trading strategy to change logic without retraining
  • Added retraining of the model on fresh history
  • Packaged it in Docker and started trading

Result

Signals are calculated on the data stream automatically, with no manual chart watching. The model is retrained on fresh history and plugged in without rewriting the bot.

Technologies

PythonPyTorchWebSocket

Tell me about your task

Telegram