# Lodestar: Supporting Independent Learning and Rapid Experimentation Through Data-Driven Analysis Recommendations

arXiv: https://arxiv.org/abs/2204.07876 · HTML: https://mlsanity.com/paper/2204.07876/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2022.

## Built on by (most cited first, 2 of 2)

- [LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution](https://mlsanity.com/paper/2411.05651/) (2024)
- [AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations](https://mlsanity.com/paper/2609.36915/) (2026)

## Abstract (arXiv)

Keeping abreast of current trends, technologies, and best practices in visualization and data analysis is becoming increasingly difficult, especially for fledgling data scientists. In this paper, we propose Lodestar, an interactive computational notebook that allows users to quickly explore and construct new data science workflows by selecting from a list of automated analysis recommendations. We derive our recommendations from directed graphs of known analysis states, with two input sources: one manually curated from online data science tutorials, and another extracted through semi-automatic analysis of a corpus of over 6,000 Jupyter notebooks. We evaluate Lodestar in a formative study guiding our next set of improvements to the tool. Our results suggest that users find Lodestar useful for rapidly creating data science workflows.