# Automating Data Science: Prospects and Challenges

arXiv: https://arxiv.org/abs/2105.05699 · HTML: https://mlsanity.com/paper/2105.05699/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 63 references that are in the map.
- First posted on arXiv 12 May 2021.

## Builds on (most cited first, 10 of 10)

- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI](https://mlsanity.com/paper/1909.02309/) (2019)
- [Automatic Construction and Natural-Language Description of Nonparametric Regression Models](https://mlsanity.com/paper/1402.4304/) (2014)
- [Data Engineering for Data Analytics: A Classification of the Issues, and Case Studies](https://mlsanity.com/paper/2004.12929/) (2020)
- [Automated Machine Learning with Monte-Carlo Tree Search](https://mlsanity.com/paper/1906.00170/) (2019)
- [ColNet: Embedding the Semantics of Web Tables for Column Type Prediction](https://mlsanity.com/paper/1811.01304/) (2018)
- [BayesDB: A probabilistic programming system for querying the probable implications of data](https://mlsanity.com/paper/1512.05006/) (2015)

## Built on by (most cited first, 18 of 18)

- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks](https://mlsanity.com/paper/2306.08107/) (2023)
- [Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey](https://mlsanity.com/paper/2411.10478/) (2024)
- [Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML](https://mlsanity.com/paper/2303.08485/) (2023)
- [Position: A Call to Action for a Human-Centered AutoML Paradigm](https://mlsanity.com/paper/2406.03348/) (2024)
- [Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents](https://mlsanity.com/paper/2506.08800/) (2025)
- [EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management](https://mlsanity.com/paper/2606.03841/) (2026)
- [A Survey of Pipeline Tools for Data Engineering](https://mlsanity.com/paper/2406.08335/) (2024)
- [Machine learning's own Industrial Revolution](https://mlsanity.com/paper/2311.02278/) (2023)
- [Using ChatGPT for Data Science Analyses](https://mlsanity.com/paper/2404.08480/) (2024)
- [Capturing and Anticipating User Intents in Data Analytics via Knowledge Graphs](https://mlsanity.com/paper/2411.01023/) (2024)
- [Unveiling Interesting Insights: Monte Carlo Tree Search for Knowledge Discovery](https://mlsanity.com/paper/2510.00876/) (2025)
- [Symbolic Separation: Grounding Deep Agents in Knowledge Graphs for Trustworthy Operational Data Analytics](https://mlsanity.com/paper/2609.17107/) (2026)
- [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026)
- [The Silent Failures in Agentic Data Science](https://mlsanity.com/paper/2610.14115/) (2026)

## Abstract (arXiv)

Given the complexity of typical data science projects and the associated demand for human expertise, automation has the potential to transform the data science process. Key insights: * Automation in data science aims to facilitate and transform the work of data scientists, not to replace them. * Important parts of data science are already being automated, especially in the modeling stages, where techniques such as automated machine learning (AutoML) are gaining traction. * Other aspects are harder to automate, not only because of technological challenges, but because open-ended and context-dependent tasks require human interaction.