Nagim Ibragimov
Back to Projects
Crypto Analyser — Rule-Based Market Decision Engine
PythonQuantitativepandasBacktestingTelegram Botscikit-learn

Crypto Analyser — Rule-Based Market Decision Engine

A quantitative, rule-based market-analysis and decision-support system for crypto and FX: 10 transparent signal rules, full backtesting with no look-ahead bias, a Telegram bot front-end, and an ML pipeline in active development.

Year: 2026Category: Python

Project Overview

Crypto Analyser ingests market candle data, scores each bar against a stack of 10 deterministic quantitative rules, and produces a clear BUY / WAIT decision — with every rule's individual pass/fail shown, so nothing is hidden behind a black box. It is deliberately a decision-support tool, not an autotrader: it does the maths, quantifies risk via fixed-fractional position sizing and multi-condition exits, and presents the evidence for the human to act on. A rigorous backtester (next-bar entry, real taker fees, drawdown and buy-and-hold benchmarking) validates the rules on historical data before any real money is risked. It runs live as a scheduled Telegram monitoring bot with persistent state, and is now being extended with a scikit-learn feature/label pipeline that learns entry quality from forward-looking historical outcomes — turning the binary BUY/WAIT output into a ranked, probability-weighted signal.

Crypto Analyser — Rule-Based Market Decision Engine