# numerai/example-scripts

A collection of scripts and notebooks to help you get started quickly.

Repository: https://github.com/numerai/example-scripts
Canonical: https://ross.abutalabs.com/products/example-scripts
Homepage: https://numer.ai/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: numerai, machine-learning, quant-finance, cryptocurrency
Last push: 2026-08-22T00:58:03+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 100
- inputs: {"age_days": 3526, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1176, forks 313 (observed 2026-08-28T04:03:52.577900+00:00)

## What it is
Official starter scripts and tutorial notebooks for the Numerai data science tournament, where participants build machine learning models on obfuscated hedge-fund-grade stock market data. It includes example models (e.g., XGBoost), feature neutralization and target ensembling notebooks, model upload examples, and MCP-based agent tooling for AI-driven experimentation.

## Use cases
- get started with the numerai tournament
- build a model to predict stock market targets
- learn feature neutralization for quant models
- create an ensemble trained on multiple targets
- upload predictions to numerai
- use AI agents with numerai via MCP
- explore the numerai dataset in a notebook

## When to choose
- you are new to Numerai and want official onboarding examples
- you want working Python/R baselines for the tournament data
- you want to wire AI coding agents into Numerai workflows via MCP

## When to avoid
- you need a production trading system or backtesting framework
- you want reusable financial models outside the Numerai tournament (data is obfuscated and tournament-only)
- you need a general-purpose ML library rather than tournament examples

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, data-science, sdk, mcp, developer-tools
- domain: machine-learning, data-science, fintech, tutorials
- platform: python, cross-platform, cli
- tags: numerai, quant-finance, jupyter-notebooks, tournament, example-scripts, stock-market-prediction, xgboost, numerapi, cryptocurrency

## Member repositories
- numerai/example-scripts (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:52.577900+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:26:35.797121+00:00, confidence not recorded.
  - readme: https://github.com/numerai/example-scripts (fetched 2026-08-28T04:03:52.577900+00:00, sha f0e3871f8a3c)
  - homepage: https://numer.ai/ (fetched 2026-08-29T12:33:18.503167+00:00, sha 6b3acdebd83b)
  - site_page: https://docs.numer.ai/ (fetched 2026-08-29T12:33:18.505719+00:00, sha 268c230562d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.