Research Article

Integrating Data Science into Project-Based Learning for Regional Problem Solving: A Practical Case Study

Yasuki Tsuchiya 1 * , Ken-ichi Yasue 1
More Detail
1 Faculty of Sustainable Design, University of Toyama, Toyama 930-8555, Japan* Corresponding Author
Educational Innovations and Emerging Technologies, 6(3), September 2026, 68-75, https://doi.org/10.35745/eiet2026v06.03.0009
Submitted: 08 March 2026, Published: 24 September 2026
OPEN ACCESS   10 Views   7 Downloads
Download Full Text (PDF)

ABSTRACT

Regional universities are increasingly expected to contribute to local problem-solving while cultivating practical competencies in students. However, effectively integrating data science (DS) into Project-Based Learning (PBL) remains challenging due to operational and institutional barriers. This study presents a practical framework for "DS-enhanced PBL" based on the educational practices at the School of Sustainable Design, University of Toyama. In the "Regional Design PBL" course, students collaborate with local governments and private sectors to address real-world issues. To overcome the high technical barriers for students and the instructional workload for faculty, we introduced a "circulating support" model led by a dedicated DS instructor. Through the analysis of four representative cases—disaster information sharing, spatial evaluation of emergency supply warehouses, congestion mitigation in the university cafeteria, and wildlife monitoring using IoT—this study demonstrates how specialized technical support enables students to construct evidence-based arguments and develop feasible regional proposals. The findings suggest that a systematic support structure is a decisive factor in sustaining interdisciplinary DS-oriented PBL, offering a viable model for advancing data-driven higher education in regional settings.
Keywords: Project-based learning (PBL), Data science education, GIS analysis, IoT monitoring, Regional problem solving

CITATION (APA)

Tsuchiya, Y., & Yasue, K.-I. (2026). Integrating Data Science into Project-Based Learning for Regional Problem Solving: A Practical Case Study. Educational Innovations and Emerging Technologies, 6(3), 68-75. https://doi.org/10.35745/eiet2026v06.03.0009

REFERENCES

  1. Cabinet Office, Government of Japan. (2022). AI Strategy 2022 (in Japanese). Available online: https://www8.cao.go.jp/cstp/ai/index.html (accessed on December 15, 2025).
  2. Clausen, N. R., Hansen, S., Guldholt, K., Poulsen, B., & Bertel, L. (2025). Transitioning to project-based learning in data science education: An action research study at a Danish vocational school. In Proceedings of the International Research Symposium on Problem-Based Learning (IRSPBL), Pretoria, South Africa, November 17–21, 2025. https://doi.org/10.54337/irspbl-11119.
  3. Consortium for Strengthening Mathematics, Data Science, and AI Education. (2025). Overview of survey results on the current status and challenges of PBL education: Survey on implementation status of mathematics, data science, and AI education (in Japanese). Consortium Newsletter, 23, 3–5. Available online: https://www.mi.u-tokyo.ac.jp/consortium/pdf/NewsLetter_vol23_survey.pdf (accessed on December 15, 2025).
  4. Huang, W., London, J. S., & Perry, L. A. (2022). Project-based learning promotes students’ perceived relevance in an engineering statistics course: A comparison of learning in synchronous and online learning environments. Journal of Statistics and Data Science Education, 31(2), 179–187. https://doi.org/10.1080/26939169.2022.2128119.
  5. Kimura, A., Tsuchiya, Y., & Yasue, K. (2024). Evacuation route analysis of evacuation drills using GIS in the hilly and mountainous area: From the overlay with the actual damaged points (in Japanese). Reports of the City Planning Institute of Japan, 23(2), 122–128. https://doi.org/10.11361/reportscpij.23.2_122.
  6. Kolaczyk, E. D., Wright, H., & Yajima, M. (2021). Statistics practicum: Placing “practice” at the center of data science education. Harvard Data Science Review, 3(1). https://doi.org/10.1162/99608f92.2d65fc70.
  7. Sakamaki, K., Matsui, T., Nishiuchi, H., Akimoto, Y., & Koizumi, K. (2022). Experience of distance education for project-based learning in data science. Japanese Journal of Statistics and Data Science, 5, 757–767. https://doi.org/10.1007/s42081-022-00154-2.
  8. Yamasaki, M., Tsuchiya, Y., & Yasue, K. (2025). Analysis of wild animal appearances in the Sendanyama area using IoT camera. In Proceedings of the 2025 International Conference of Asia-Pacific Planning Societies, Hsinchu City, Taiwan, August 21, 2025.