УКР
ENG
Search


Data Analysis Using Generative AI: Opportunities and Challenges
Skitsko V. I.

Skitsko, Volodymyr I. (2023) “Data Analysis Using Generative AI: Opportunities and Challenges.” The Problems of Economy 4:217–225.
https://doi.org/10.32983/2222-0712-2023-4-217-225

Section: Mathematical methods and models in economy

Article is written in Ukrainian
Downloads/views: 0

Download article in pdf format -

UDC 004.8:311

Abstract:
The article examines topical issues of using generative artificial intelligence, in particular large language models ChatGPT and Claude, for data analysis. The essence of the term «artificial intelligence» changes over time. And if earlier, when using this term, was talked about expert systems, machine learning, etc., now this term means primarily large language models, among which the most famous are ChatGPT, Claude, Bing, Bard. These models allow you to generate texts, images, audio, and video based on user requests. The purpose of the article is to explore the opportunities and challenges of using ChatGPT and Claude in data analysis based on existing publications and our own experience. After all, the ability of large language models to communicate in natural language makes them a powerful analytics tool. The paper considers aspects of the main stages of data analysis in the context of the use of large language models: obtaining, collecting and loading input data, their pre-processing, application of mathematical models, visualization and interpretation of results. Practical recommendations for formulating requests to ChatGPT and Claude at each stage of data analysis are provided. It is noted that ChatGPT, thanks to the built-in Advanced Data Analysis service, allows an effectively analysis of data, powered by Python language. This provides higher accuracy of results compared to other large language models. Using a conditional example, a comparison of the capabilities of ChatGPT and Claude in data analysis is carried out. It is shown that ChatGPT allows you to build dependency models, generate graphs and give meaningful explanations of the results obtained. At the same time, Claude’s capabilities in data analysis are quite limited. It is concluded that ChatGPT has significantly greater potential for data analysis compared to Claude and other chatbots. However, so far, large language models cannot completely replace data analysts and powerful decision support systems. In further research, it is proposed to focus on the study of the practical application of the capabilities of ChatGPT and, in particular, its Advanced Data Analysis service to solve various data analysis problems.

Keywords: data analysis, generative artificial intelligence, large language models, ChatGPT, Claude.

Fig.: 11. Bibl.: 19.

Skitsko Volodymyr I. – Candidate of Sciences (Economics), Associate Professor, Associate Professor, Department of Mathematical Modeling and Statistics, Kyiv National Economic University named after Vadym Hetman (54/1 Beresteiskyi Ave., Kyiv, 03057, Ukraine)
Email: skitsko.kneu@gmail.com

List of references in article

“Dartmouth workshop“. Wikipedia. https://en.wikipedia.org/wiki/Dartmouth_workshop
“Artificial Intelligence“. Wikipedia. https://en.wikipedia.org/wiki/Artificial_intelligence
“ChatGPT“. OpenAI. https://chat.openai.com/
“Bard“ Google. https://bard.google.com/
“Bing“ Microsoft. https://www.bing.com/
“Copilot“ Microsoft. https://copilot.microsoft.com/
“Claude“ Anthropic. https://claude.ai/chats
Hans, F. “Automating Data Analytics with Large Language Models“. medium.com. October 11, 2023. https://medium.com/@felixbastian.hans/automating-data-analytics-with-large-language-models-3e83bcdbd51d
Olumide, S. “How to Use ChatGPT - Prompts for Data Scientists“. freeCodeCamp. April 24, 2023. https://www.freecodecamp.org/news/how-to-use-chatgpt-for-data-scientists/
Cox, T. “How to Use ChatGPT for Data Analysis in Ecommerce“ Swanky. July 26, 2023. https://swankyagency.com/chatgpt-for-data-analysis/
Awan, A. A. “The 10 Best ChatGPT Plugins for Data Science“. Datacamp. July 2023. https://www.datacamp.com/blog/the-10-best-chat-gpt-plugins-for-data-science
Awan, A. A. “Claude vs ChatGPT for Data Science: A Comparative Analysis“. Datacamp. Juny 2023. https://www.datacamp.com/blog/claude-vs-chatgpt-data-science-comparison
Awan, A. A. “Top 10 Data Science Tools To Use in 2024“. Datacamp. November 2023. https://www.datacamp.com/blog/top-data-science-tools
Downing, C. “How to Use ChatGPT's Advanced Data Analysis Feature“. MIT Sloan Teaching & Learning Technologies. https://mitsloanedtech.mit.edu/ai/tools/data-analysis/how-to-use-chatgpts-advanced-data-analysis-feature/
“AI Prompts for Data Analysis“. AnalyticsHacker. https://www.analyticshacker.com/analytics-resources/ai-prompts-for-data-analysis
“ChatGPT Excel Functions“. Apps Do Wonders. https://appsdowonders.com/chatgpt-for-excel-functions/
“All available functions in GPT for Excel“. Talarian. https://gptforwork.com/help/gpt-for-excel/gpt-functions/all-available-functions
“All available functions in GPT for Sheets“. Talarian. https://gptforwork.com/help/gpt-for-sheets/gpt-functions/all-available-functions
“What Is Data and Analytics?“ Gartner. https://www.gartner.com/en/topics/data-and-analytics

  The Promblems of Economy, 2009-2024 The site and its metadata are licensed under CC-BY-SA. Write to webmaster