[2404.08480] Using ChatGPT for Data Science Analyses

Computer Science > Machine Learning arXiv:2404.08480 (cs) [Submitted on 12 Apr 2024 (v1), last revised 2 Mar 2026 (this version, v2)] Title:Using ChatGPT for Data Science Analyses Authors:Ozan Evkaya, Miguel de Carvalho View a PDF of the paper titled Using ChatGPT for Data Science Analyses, by Ozan Evkaya and 1 other authors View PDF HTML (experimental) Abstract:As a result of recent advancements in generative AI, the field of data science is prone to various changes. The way practitioners construct their data science workflows is now irreversibly shaped by recent advancements, particularly by tools like OpenAI's Data Analysis plugin. While it offers powerful support as a quantitative co-pilot, its limitations demand careful consideration in empirical analysis. This paper assesses the potential of ChatGPT for data science analyses, illustrating its capabilities for data exploration and visualization, as well as for commonly used supervised and unsupervised modeling tasks. While we focus here on how the Data Analysis plugin can serve as co-pilot for Data Science workflows, its broader potential for automation is implicit throughout. Comments: Subjects: Machine Learning (cs.LG); Computation and Language (cs.CL); Computation (stat.CO) Cite as: arXiv:2404.08480 [cs.LG]   (or arXiv:2404.08480v2 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2404.08480 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Harvard Data Science Review, 8(1) (2026) Relate...