mlsanityData to 7 Oct 2026

AutoDS: Towards Human-Centered Automation of Data Science

arXiv 2101.05273 ↗First posted 13 Jan 2021cs.HC cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Data science (DS) projects often follow a lifecycle that consists of laborious tasks for data scientists and domain experts (e.g., data exploration, model training, etc.). Only till recently, machine learning(ML) researchers have developed promising automation techniques to aid data workers in these tasks. This paper introduces AutoDS, an automated machine learning (AutoML) system that aims to leverage the latest ML automation techniques to support data science projects. Data workers only need to upload their dataset, then the system can automatically suggest ML configurations, preprocess data, select algorithm, and train the model. These suggestions are presented to the user via a web-based graphical user interface and a notebook-based programming user interface. We studied AutoDS with 30 professional data scientists, where one group used AutoDS, and the other did not, to complete a data science project. As expected, AutoDS improves productivity; Yet surprisingly, we find that the models produced by the AutoDS group have higher quality and less errors, but lower human confidence scores. We reflect on the findings by presenting design implications for incorporating automation techniques into human work in the data science lifecycle.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 13 of its 67 references that are in the map. First posted on arXiv 13 Jan 2021.

Builds on

13 of 67 references.

References · 13

  1. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  2. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  3. 2019Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AIcited by 79
  4. 2020How do Data Science Workers Collaborate? Roles, Workflows, and Toolscited by 64
  5. 2019An ADMM Based Framework for AutoML Pipeline Configurationcited by 47
  6. 2017One button machine for automating feature engineering in relational databasescited by 32
  7. 2019How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?cited by 30
  8. 2017Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loopcited by 26
  9. 2019AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinatescited by 24
  10. 2019ATMSeer: Increasing Transparency and Controllability in Automated Machine Learningcited by 23
  11. 2021How Much Automation Does a Data Scientist Want?cited by 20
  12. 2019Benchmark and Survey of Automated Machine Learning Frameworkscited by 18
1 more
  1. 2019Multi-Armed Bandits with Fairness Constraints for Distributing Resources to Human Teammatescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 7; 2023: 5; 2024: 8; 2025: 5; 2026: 3.

32 papers.

Sort:

By area:

  1. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  2. 2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Modelscited by 57
  3. 2024Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decompositioncited by 29
  4. 2023Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressionscited by 23
  5. 2023Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiencescited by 21
  6. 2024Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuningcited by 21
  7. 2021Fast and Informative Model Selection using Learning Curve Cross-Validationcited by 15
  8. 2022Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Workcited by 15
  9. 2021Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoMLcited by 12
  10. 2023Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Makingcited by 11
  11. 2022XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learningcited by 8
  12. 2023AutoML in The Wild: Obstacles, Workarounds, and Expectationscited by 8
20 more
  1. 2025SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Sciencecited by 7
  2. 2024Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategycited by 5
  3. 2025FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategiescited by 5
  4. 2022Efficient Human-in-the-loop System for Guiding DNNs Attentioncited by 4
  5. 2022Visual Analysis of Neural Architecture Spaces for Summarizing Design Principlescited by 3
  6. 2021Human-Centered AI for Data Science: A Systematic Approachcited by 2
  7. 2023OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML Systemcited by 2
  8. 2025Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimizationcited by 2
  9. 2025What Makes LLM Agent Simulations Useful for Policy Practice? An Iterative Design Study in Emergency Preparednesscited by 2
  10. 2026Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Searchcited by 2
  11. 2021Naive Automated Machine Learning -- A Late Baseline for AutoMLcited by 1
  12. 2022Practitioner Motives to Use Different Hyperparameter Optimization Methodscited by 1
  13. 2024Evolving machine learning workflows through interactive AutoMLcited by 1
  14. 2022Assessment of cognitive characteristics in intelligent systems and predictive abilitycited by 0
  15. 2024Human-Centered AI Product Prototyping with No-Code AutoML: Conceptual Framework, Potentials and Limitationscited by 0
  16. 2024Trust Your Gut: Comparing Human and Machine Inference from Noisy Visualizationscited by 0
  17. 2024How to Measure Human-AI Prediction Accuracy in Explainable AI Systemscited by 0
  18. 2025DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignalscited by 0
  19. 2026MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systemscited by 0
  20. 2026ORCA: Evaluating LLMs on Data Science Code Translationcited by 0