Implementation of a Hybrid Fuzzy SAW and Particle Swarm Optimization Algorithm for a Dynamic Laptop Recommendation System Based on User Preferences

Abstract

Recommendation systems often struggle to balance personalization with fairness, particularly in addressing the marginalization of minority brands caused by data and algorithmic biases. This study tackles that challenge by developing a dynamic laptop recommendation system tailored to user preferences, leveraging a hybrid algorithm that combines Fuzzy Simple Additive Weighting (Fuzzy SAW) and Particle Swarm Optimization (PSO). Fuzzy SAW is employed to manage uncertainties in subjective preferences such as budget and intended use, while PSO dynamically optimizes the weight of each criterion to enhance personalization. Evaluation was conducted using primary data from 27 respondents in Lhokseumawe, Aceh, collected via surveys and interviews, alongside secondary data on laptop specifications retrieved from the Tokopedia API. The resulting match accuracy reached 74.1%, with Asus accounting for 85.0% of the successful recommendations. In contrast, brands like Lenovo and Advan were significantly underrepresented, underscoring the system’s limited sensitivity to minority brands. This research contributes to the field of recommendation systems by empirically demonstrating the trade-off between optimization and fairness, as well as proposing strategies to mitigate algorithmic bias. Practical implications include better-informed user decisions and fairer brand exposure for e-commerce platforms. Future improvements will focus on expanding data sources and refining PSO parameter tuning to better accommodate underrepresented brands.