Implementation of an Early Warning System (SATA-SEEK) to prevent school dropout using DeepSeek: An approach for users without AI expertise
Keywords:
DeepSeek, Artificial Intelligence, School Dropout.Abstract
Given the increasing dropout rate in educational institutions, there is a growing need to implement new technologies. One such technology is artificial intelligence (AI), which enables the identification of students most likely to drop out. Identifying these students is a challenging task, as it involves analyzing large amounts of data, from grades in all subjects to responses to psychosocial tests. Furthermore, this task must be performed several times during the school year. Unfortunately, educational institutions often have too few staff members to carry out this task. Moreover, these staff members generally lack the specialized training in AI and the quantitative skills necessary to develop a statistical model that predicts which students are most likely to drop out. Therefore, the objective of this work was to implement an early warning system for school dropout, called SATA-SEEK. This system is based on the use of the DeepSeek chatbot. The innovation of this work lies in presenting a simple methodology that can be replicated by users without expertise in statistics or AI. The system is implemented in five stages. Key findings include the development of an early warning system to identify students at higher risk of dropping out of school. The methodology is simple enough to be implemented in any educational institution. Furthermore, it can help improve criteria for awarding scholarships. In conclusion, this system made it possible to reduce the school dropout rate to 10%.
Keywords: DeepSeek, Artificial Intelligence, School Dropout.
References
Bolaño García, M. y Duarte Acosta, N. (2024). Una revisión sistemática del uso de la inteligencia artificial en la educación. Rev. Colomb. Cir.; 39:51-63. https://doi.org/10.30944/20117582.2365
Castillejos, B. (2022). Inteligencia artificial y entornos personales de aprendizaje: atentos al uso adecuado de los recursos tecnológicos de los estudiantes universitarios. Educación XXXI(60), pp. 9-24/e-ISSN 2304-4322. https://doi.org/10.18800/educacion.202201.001
Chang, E.Y. (2023). Prompting large language models with the socratic method, in: 2023 IEEE 13 th Annual Computing and Communication Workshop and Conference, CCWC 2023,. pp. 351-360. https://doi.org/10.1109/CCWC57344.2023.10099179
Dempere J, Modugu K, Heshman A & Ramasamy LK (2023) The impact of ChatGPT on higher education. Front. Educ. 8:1206936. doi: https://doi.org/10.3389/feduc.2023.1206936
Drenon, N., Gerken, T., Cieslak, M. (2025). DeepSeek: the Chinese AI app that has the world talking. BBC News. https://www.bbc.com/news/articles/c5yv5976z9po
Finkel, L., Parra-Contreras, P., Martínez-Solana, Y. y Matos-Mejías, C. (2024). ChatGPT como fuente de información en la Educación Superior valoración de los resultados que proporciona la IA generativa. Profesional de la información. ISSN: 1386-6710, 1699-2407. Vol. 33. No. 4. DOI:
https://doi.org/10.3145/EPI.2024.0604
Heston, T.F., and Khun, C. (2023). Prompt engineering in medical education. Int. Med. Educ., 2(3), pp. 198-205. https://doi.org/10.3390/ime2030019
Giray, L., (2023). Prompt engineering with ChatGPT: a guide for academic writers, Ann. Biomed. Eng. DOI: https://doi.org/10.1007/s10439-023-03272-4
IGECEM (2023). Instituto de Información e Investigación Geográfica, Estadística y Catastral del Estado de México. Estadística Básica Municipal del Estado de México Amecameca. Gobierno del Estado de México. CE 207/09/06/23 P. 6.
INEGI (Noviembre de 2024). Página Web Oficial del Instituto Nacional de Estadística, Geografía e Informática. https://www.inegi.org.mx/app/tabulados/interactivos/?px=Educacion_11&bd=Educacion
INEGI (2025). Página Web Oficial del Instituto Nacional de Estadística, Geografía e Informática. https://www.inegi.org.mx/app/areasgeograficas/?ag=15#collapse-Resumen
Lo, L.S. (2023). The art and science of prompt engineering: a new literacy in the information age, Internet Ref. Serv. Q., 2023. DOI: https://doi.org/10.1080/10875301.2023.2227621
Martínez-Acuña, V., Valadez-Morales, H. y Coronado-González, Y. (2024). Innovación Educativa: La IA como herramienta para prevenir el abandono escolar. Vol. 11. Memorias del Concurso Lasallista de Investigación, Desarrollo e Innovación. DOI: https://doi.org/10.26457/mclidi.v11i2.4294
Ming Sin Wong, J. (2025). Speculative futures of education: utopian and dystopian scenarios envisioned by Chatgpt, Gemini, and Deepseek. Wong Discover Education. 4:261. https://doi.org/10.1007/s44217-025-00692-3
Mujica-Sequera, R. (2025). Los Prompts de IA: Herramientas para la Optimización de la Investigación Científica. International Journal Technological-Educational, 18(1) pp. 267-277, ISSN: 2665-0266. https://doi.org/10.37843/rted.v18i1.61
Peñalver-Higuera, M., Rodríguez-Alegre, L., López-Padilla, R., Isea-Argüelles, J. (2025). Ingeniería de prompts en la industria 4.0: Optimización y automatización inteligente de procesos industriales. Revista Electrónica Multidisciplinaria de Ciencias Básicas, Ingeniería y Arquitectura, 7(12). https://doi.org/10.35381/i.p.v7i12.4438
Tianchen Gao, Jiashun Jin, Zheng Tracy Ke, Gabriel Moryoussef. (2025). A Comparison of DeepSeek and Other LLMs. Computation and Language. https://doi.org/10.48550/arXiv.2502.03688
Velásquez-Henao, J.D., Franco-Cardona, C.J. and Cadavid-Higuita, L. (2023). Enineering: a methodology for optimizing interactions with AI-Language Models in the field of engineering. DYNA, 90 (230), pp. 9-17. https://doi.org/10.15446/dyna.v90n230.111700
Velásquez-Henao, J., Franco-Cardona, C., Cadavid-Higuita, L. (2024). Ingeniería de instrucciones: una metodología para optimizar interacciones con Modelos de Lenguaje de IA en el campo de ingeniería. DYNA, 90, pp. 9-17. ISSN 0012-7353. https://doi.org/10.15446/dyna.v90n230.111700
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., Schmidt, D. (2023). A prompt pattern catalog to enhance prompt engineering with chatgpt, ArXiv Prepr. https://doi.org/10.48550/arXiv.2302.11382
Zavala Cárdenas, E., Salazar Guaraca, D., Albán Yánez, E. y Mayorga Albán, A. (2023). El rol de la inteligencia artificial en la enseñanza-aprendizaje de la educación superior. Pol. Con. (Edición núm. 80) Vol. 8, No 3. https://dialnet.unirioja.es/servlet/articulo?codigo=9252162
