Applications of artificial intelligence in the teaching of statistics and operational research

• Miguel Escribano ^[1] ; Juan Jose Escribano ^[2]
  1. [1] Universidad Complutense de Madrid

     Universidad Complutense de Madrid

     Madrid, España

     
  2. [2] Universidad Nacional de Educación a Distancia

     Universidad Nacional de Educación a Distancia

     Madrid, España

     
• Localización: BEIO, Boletín de Estadística e Investigación Operativa, ISSN 1889-3805, Vol. 41, Nº. 3, 2025, págs. 53-63
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • This study focuses on the application of Generative Artificial Intelligence (GAI) in problem-solving within the fields of statistics and operations research. The primary objective is the automatic generation of code capable of effectively addressing specific issues in these domains. To this end, the methodology adopted is prompt engineering, which enables the precise formulation of problems from a perspective oriented towards the specification of requirements for the software to be developed.

    The introductory section contextualizes the role of GAI, emphasizing its objectives and its relevance within the scope of this work. Furthermore, a review of the state of the art is conducted to position this research within the context of previous related studies. The methodology section details the approach employed for the construction of prompts, which serve as input for GAI models.

    Subsequently, several case studies in the fields of operations research and statistics are presented. For each case, the employed prompt, the code generated by the GAI model, and the outcome of its execution are provided, with the aim of illustrating the practical resolution of the proposed problems.

    The results obtained demonstrate that the proposed methodology is viable for solving the selected problems and allows for the generation of functional models that facilitate the validation of the provided solutions.

• Referencias bibliográficas
  • Cotroneo, D., Foggia, A., Improta, C., Liguori, P. y Natella, R. (2024). Automating the correctness assessment of AI-generated code for security...
  • Garg, A., Nisumba Soodhani, K. y Rajendran, R. (2025). Enhancing data analysis and programming skills through structured prompt training:...
  • Gupta, A. y Shivers-McNair, A. (2024). “Wayfinding” through the AI wilderness: Mapping rhetorics of CHATGPT prompt writing on X (formerly...
  • Khalifa, M. y Albadawy, M. (2024). Using artificial intelligence in academic writing and research: An essential productivity tool. Computer...
  • Kizilcec, R. F., Huber, E., Papanastasiou, E. C., Cram, A., Makridis, C. A., Smolansky, A., . . . Raduescu, C. (2024). Perceived impact of...
  • Kohnke, L., Moorhouse, B. L. y Zou, D. (2023). Exploring generative artificial intelligence preparedness among university language instructors:...
  • Liguori, P., Improta, C., Natella, R., Cukic, B. y Cotroneo, D. (2023). Who evaluates the evaluators? On automatic metrics for assessing AI-based...
  • Nayyar, A. (2025). Mastering prompt engineering: Deep Insights for optimizing large language models - LLMS. Morgan Kaufmann.
  • Nazir, A. y Wang, Z. (2023). A comprehensive survey of chatgpt: Advancements, applications, prospects, and challenges. MetaRadiology, 1(2),...
  • Park, A. y Kim, T. (2025). Code suggestions and explanations in programming learning: Use of CHATGPT and performance. The International Journal...
  • Peres, R., Schreier, M., Schweidel, D. y Sorescu, A. (2023). On Chatgpt and beyond: How generative artificial intelligence may affect research,...
  • Rodrigues do Nascimento Junior, E. (2024). Generative AI and the future of education: Ragnarok or reformation? A paradoxical perspective from...
  • Yilmaz, R. y Karaoglan Yilmaz, F. G. (2023). The effect of Generative Artificial Intelligence (AI)-based tool use on students’ computational...