Fuzzy Piecewise Logistic Growth Model for Innovation Diffusion: A Case Study of the TV Industry

• Published in: International journal of fuzzy systems Vol. 18; no. 3; pp. 511 - 522
• Main Authors: Yu, Jing Rung, Tseng, Fang-Mei
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2016; Springer Nature B.V
• Subjects: Artificial Intelligence; Computational Intelligence; Engineering; Growth models; Innovations; Linear programming; Logit models; Management Science; Market shares; Operations Research; Product development; Product life cycle; Regression analysis; Regression models; S curves; Statistical analysis; Television; Variables; Fuzzy piecewise regression; Multiple objective programming; Logistic model
• ISSN: 1562-2479; 2199-3211
• DOI: 10.1007/s40815-015-0066-8

The logistic model is adopted in order to fit growth trends of innovative products for a single growth process. In the current competitive environment, we are incapable of predicting a product’s life cycle such that it can be described as a smooth S curve. Given this, we propose the use of a fuzzy piecewise regression model as a revision of the traditional logistic model. While no proper probability distribution for market share data currently exists, the proposed method is not only able to detect change-points, but can also identify predicted intervals when the growth trend of an analyzed generation is affected by other product generations. The market shares of four television technologies are used in order to demonstrate the performance of the proposed model. The results show that the proposed model outperforms the logistic model, providing both the best and worst possible market shares for the corresponding generation, and highlighting the time of impact of external influences by identifying change-points.