This workshop will evaluate and discuss the performance and limitations of OpenAI's Advanced Data Analytics tool in data science tasks, usin
Room 2.55, Edinburgh Futures Institute, The University of Edinburgh
1 Lauriston Place Edinburgh EH3 9EF United KingdomAs a result of recent advancements in generative AI (GenAI), the field of data science is prone to various changes. Data Analysis (DA) capabilities of the ChatGPT and its competitors are getting more powerful based on the recent developments in the field of GenAI.
While DA provides researchers and practitioners with unprecedented analytical capabilities, it is far from being perfect, and it is important to recognize and address its limitations.
A key goal of this project is to evaluate the performance of the OpenAI Advanced Data Analytics (ADA) tool on Data Science tasks (e.g., data wrangling, exploratory analyses, fitting models). For this purpose, OpenAI Code Interpreter assistant will be used for the specific tasks repeatedly by mimicking the idea of Monte Carlo experiments borrowed from the field of Statistics.
This talk aims to summarize the recent findings of a GAIL seed-funded project, sharing some experimental resultswith practitioners and academics and gathering specific feedback from those in attendance.
The workshop will be led by Dr Ozan Evkaya, GAIL Fellow and University Teacher in Statistics.