@inproceedings{10.1145/3708635.3708655,
author = {Yu, Hong Qing and Sutton, Jack and O'Neill, Sam and Reiff-Marganiec, Stephan},
title = {Case Studies on LLM Centric and Services Oriented Data Analytics Agent Development},
year = {2025},
isbn = {9798400717765},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3708635.3708655},
doi = {10.1145/3708635.3708655},
abstract = {This paper presents a novel service orchestration framework for a chatbot application focused on data analytics questions. The framework integrates Large Language Models (LLMs) with service-oriented computing to transform data analytics into a dynamic, conversational experience. The approach leverages advancements in LLM technology to enable real-time, automated data insights via chatbot interfaces, making complex data analytics accessible across various industries. In addition, the data will be processed and analysis at edge-machine rather than post all the data directly to the LLMs on the cloud. Therefore, the Central to the framework is the local Micro Analytics Service (MAS) and a dynamic service-data coordination framework, which together facilitate the decoupling of data from business logic, allowing for intuitive engagement with analytics processes. Through two case studies, retail data analysis and regional healthcare planning, the ability of the framework to provide actionable insights through natural language prompts is demonstrated, showcasing its potential to significantly reduce barriers to sophisticated data analytics. The evaluation reveals strong performance in data connection and code generation, with identified areas for improvement in visualizations and handling complex data scenarios.},
booktitle = {Proceedings of the 2024 13th International Conference on Software and Information Engineering},
pages = {69–76},
numpages = {8},
keywords = {LLM-driven service orchestration, Dynamic data analytics services, Services Computing},
location = {
},
series = {ICSIE '24}
}

{"_id":"pbNNar3HNoFr7FHRQ","bibbaseid":"yu-sutton-oneill-reiffmarganiec-casestudiesonllmcentricandservicesorienteddataanalyticsagentdevelopment-2025","author_short":["Yu, H. Q.","Sutton, J.","O'Neill, S.","Reiff-Marganiec, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong","Qing"],"suffixes":[]},{"propositions":[],"lastnames":["Sutton"],"firstnames":["Jack"],"suffixes":[]},{"propositions":[],"lastnames":["O'Neill"],"firstnames":["Sam"],"suffixes":[]},{"propositions":[],"lastnames":["Reiff-Marganiec"],"firstnames":["Stephan"],"suffixes":[]}],"title":"Case Studies on LLM Centric and Services Oriented Data Analytics Agent Development","year":"2025","isbn":"9798400717765","publisher":"Association for Computing Machinery","address":"New York, NY, USA","url":"https://doi.org/10.1145/3708635.3708655","doi":"10.1145/3708635.3708655","abstract":"This paper presents a novel service orchestration framework for a chatbot application focused on data analytics questions. The framework integrates Large Language Models (LLMs) with service-oriented computing to transform data analytics into a dynamic, conversational experience. The approach leverages advancements in LLM technology to enable real-time, automated data insights via chatbot interfaces, making complex data analytics accessible across various industries. In addition, the data will be processed and analysis at edge-machine rather than post all the data directly to the LLMs on the cloud. Therefore, the Central to the framework is the local Micro Analytics Service (MAS) and a dynamic service-data coordination framework, which together facilitate the decoupling of data from business logic, allowing for intuitive engagement with analytics processes. Through two case studies, retail data analysis and regional healthcare planning, the ability of the framework to provide actionable insights through natural language prompts is demonstrated, showcasing its potential to significantly reduce barriers to sophisticated data analytics. The evaluation reveals strong performance in data connection and code generation, with identified areas for improvement in visualizations and handling complex data scenarios.","booktitle":"Proceedings of the 2024 13th International Conference on Software and Information Engineering","pages":"69–76","numpages":"8","keywords":"LLM-driven service orchestration, Dynamic data analytics services, Services Computing","location":"","series":"ICSIE '24","bibtex":"@inproceedings{10.1145/3708635.3708655,\nauthor = {Yu, Hong Qing and Sutton, Jack and O'Neill, Sam and Reiff-Marganiec, Stephan},\ntitle = {Case Studies on LLM Centric and Services Oriented Data Analytics Agent Development},\nyear = {2025},\nisbn = {9798400717765},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3708635.3708655},\ndoi = {10.1145/3708635.3708655},\nabstract = {This paper presents a novel service orchestration framework for a chatbot application focused on data analytics questions. The framework integrates Large Language Models (LLMs) with service-oriented computing to transform data analytics into a dynamic, conversational experience. The approach leverages advancements in LLM technology to enable real-time, automated data insights via chatbot interfaces, making complex data analytics accessible across various industries. In addition, the data will be processed and analysis at edge-machine rather than post all the data directly to the LLMs on the cloud. Therefore, the Central to the framework is the local Micro Analytics Service (MAS) and a dynamic service-data coordination framework, which together facilitate the decoupling of data from business logic, allowing for intuitive engagement with analytics processes. Through two case studies, retail data analysis and regional healthcare planning, the ability of the framework to provide actionable insights through natural language prompts is demonstrated, showcasing its potential to significantly reduce barriers to sophisticated data analytics. The evaluation reveals strong performance in data connection and code generation, with identified areas for improvement in visualizations and handling complex data scenarios.},\nbooktitle = {Proceedings of the 2024 13th International Conference on Software and Information Engineering},\npages = {69–76},\nnumpages = {8},\nkeywords = {LLM-driven service orchestration, Dynamic data analytics services, Services Computing},\nlocation = {\n},\nseries = {ICSIE '24}\n}\n\n","author_short":["Yu, H. Q.","Sutton, J.","O'Neill, S.","Reiff-Marganiec, S."],"key":"10.1145/3708635.3708655","id":"10.1145/3708635.3708655","bibbaseid":"yu-sutton-oneill-reiffmarganiec-casestudiesonllmcentricandservicesorienteddataanalyticsagentdevelopment-2025","role":"author","urls":{"Paper":"https://doi.org/10.1145/3708635.3708655"},"keyword":["LLM-driven service orchestration","Dynamic data analytics services","Services Computing"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/CLxDQpCeqT3TztuJd","dataSources":["jiG55yeh3DWJSJSKY","fDYJKswSSdMyrf6yj","i23wvNL5dYaE5y5cH"],"keywords":["llm-driven service orchestration","dynamic data analytics services","services computing"],"search_terms":["case","studies","llm","centric","services","oriented","data","analytics","agent","development","yu","sutton","o'neill","reiff-marganiec"],"title":"Case Studies on LLM Centric and Services Oriented Data Analytics Agent Development","year":2025}