Multiple Affective Attributes for the Customization of Post-Pandemic Food Services

Customization of multiple attributes is an innovative strategy to adapt to the uncertain situation in the post-pandemic food services. It is a nondeterministic polynomial-time NP-hard multi-criteria decision-making problem which requires Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO). Attributes data were acquired using Kansei words through online in-depth interview and questionnaire. A total of 505 respondents were recruited from the five biggest islands in Indonesia. The data were modeled using an artificial neural network to predict the importance of the attributes. The predicted importance was optimized using Particle Swarm Optimization (PSO) based on the pandemic constraints of anxiety, familiarity, and trust. The PSO extracted 4, 12, and 3 attributes for dine-out, delivery, and take-out services, respectively. The findings of this study could help industries in minimizing research and development costs by utilizing the extracted affective attributes.