Eiten
It implements eigen, minimum-variance, maximum-Sharpe, and genetic-algorithm portfolio strategies.
AI INVEST MAP · TOOLS & RESEARCH GUIDES
Tools for market data, investment research and strategy backtesting.
Recommendations prioritize relevant official financial Skills. Selected markets take priority over language preferences; language does not establish your location or eligibility.
It implements eigen, minimum-variance, maximum-Sharpe, and genetic-algorithm portfolio strategies.
It analyzes trading or backtest results and can be used alongside Zipline workflows.
Its Jupyter notebooks connect financial economics with mathematics, statistics, scientific computing, and data-analysis packages.
It covers the full workflow for designing, implementing, evaluating, and deploying reinforcement-learning trading algorithms.
It exposes many technical indicators and candlestick-pattern recognition for processing financial market data.
Experimental Polymarket CLI for market discovery, orders, positions, and on-chain operations
Supports live execution
It contains chapter-organized code and Jupyter notebooks for the book’s machine-learning-in-finance examples.
It focuses on consistent calculation methods for financial metrics and provides analysis indicators and statement-data workflows.
It experiments with algorithms and strategies on stock data, including technical and fundamental inputs to prediction.
Experimental LLM-agent lab with backtests, paper workflows, traces, and optional guarded broker execution
OpenClaw framework for hosting agent workflows; trading depends on installed integrations
It runs algorithms from the literature through one interface to compare how they choose portfolio weights over time.
Skills for natural-language strategy generation and local Hyperliquid perps backtesting
It follows the book’s examples of using machine-learning methods in Python to develop investment strategies and trading signals.
It provides a unified API for several exchange markets and links to usage examples and a simple graphical interface.
Python runtime for backtesting, paper trading, and live broker execution
Supports live execution
It supports networks that produce portfolio weights in one forward pass for research on neural allocation methods.
Crypto trading framework with support for AI strategies
Local-first, agent-agnostic journal and review harness with deterministic replay and human review gates
The course introduces Python through numerical-computing and data-visualization examples; it is not a complete programming curriculum.
Information and source links, not investment advice. Inclusion and source checks do not guarantee security, compliance or returns. How information is reviewed