Commercialization Classification Model for Research and Development Projects Using Decision Tree Technique
Main Article Content
Abstract
The objective of this research was to create a classification model for categorizing types of commercialization potential in research and development projects conducted at the Mae Moh Power Plant, Electricity Generating Authority of Thailand. This research utilized the decision tree technique to construct the classification model. Furthermore, it provided appropriate management guidelines for different commercial potentials. The sample group used to build and test the model consisted of 56 projects from Mae Moh Power Plant, invested in between the years 2008–2021. The characteristics of the sample projects used to construct the model encompass six attributes: 1) Patentability, 2) Type of Utilization, 3) Continuous real-world application ability, 4) Progression from previous projects, 5) Research institution capability, and 6) Investment size. The model's outcome involved classifying commercialization potential into three groups: High commercialization potential, Moderate commercialization potential, and Other potential. The performance of the model was tested using the 10-fold cross-validation method. With the appropriate attribute selection, the decision tree model achieved high performance with an accuracy of 96.00%, an average precision of 95.89%, and an average recall of 94.75%. Additionally, this research provided suitable management and project handling recommendations based on different commercialization potentials, aiming to maximize benefits for the organization.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.
References
R. Bandarian,“Evaluation of commercial potential of a new technology at the early stage of development with fuzzy logic,” Journal of Technology Management and Innovation, vol. 2, no. 4, pp. 73–85, 2007.
B. Kasin, “The commercialization research criteria readiness assessment,” Thesis of CITU, Thammasat University, 2018 (in Thai).
Y. Natanon and L. Wimalin, “Selecting the attributes of research and development projects that relate to commercialization potential using Business Intelligence,” in Proceedings IE Network, 2022, pp. 733–739 (in Thai).
J. R. Quinlan, Machine Learning, United States: Springer, 1986, vol. 1, pp. 81–106.
S. B. Akben, “Predicting the success of wart treatment methods using decision tree based fuzzy informative,”Biocybernetics and Biomedical Engineering, vol. 38, no. 4, pp. 819–827, 2018.
S. Mike and T. Arnesh, “The application of decision tree regression to optimize business processes,” in Proceedings ICIEM, 2021, pp. 48–57.
M. Durica, J. Frnda, and L. Svabova, “Decision tree based model of business failure prediction for Polish companies,” Oeconomia Copernicana, vol. 10, no. 3, pp. 453–469, 2019.
L. Katrina, “Decision tree analysis for law practice,” Ohio State Journal on Dispute Resolution, vol. 35, pp. 405–434, 2020.
F. A. Batarseh and R. Yang, “Confusion Matrix,” Data Democracy, United States: Academic Press, 2020, pp. 83–106.
C. Sammut and G. I. Webb, “Confusion Matrix,” Encyclopedia of Machine Learning, United States: Springer, 2011, pp. 209.
Y. Q. Duan and G. M. Cao, “An analysis of the impact of business analytic on innovation,” in Proceedings ECIS, 2015, pp. 40.