FACTORS INFLUENCING RECOMMENDER SYSTEM EFFECTIVITY ON CONTINUANCE USAGE INTENTION IN INDONESIAN E-COMMERCE USER

As global market demand grows, e-commerce platforms face an increasingly competitive environment and an ever-rising deluge of data. To sustain their operations and improve customer experience, several of these platforms have incorporated services to assist customers in sifting through mounds of information. One of these services is Recommendation System (RS), an algorithm designed to offer personalized suggestions tailored to a consumer's preference. The study intends to explore which RS factor which has the most influence on its performance and effectivity in the Indonesian e-commerce environment, one of the biggest e-commerce economies in the region. The RS factors analyzed includes: Diversity of Suggestions, Suggestion Accuracy, Suggestion Novelty, and Recommendation Quality, alongside sociological factors such as Usage Attitude, Familiarity, Trust, and Satisfaction. This study uses a modified Technology Acceptance Model (TAM) model to study the correlations between these factors, customer usage attitude, and their subsequent Continuance Usage Intention. The data is collected through questionnaires distributed to a minimum of 106 Jakarta residents, given the region’s high concentration of e-commerce users. Results show that RS quality is driven by Accuracy, Novelty, and Diversity, with Accuracy yielding the highest influence. Higher RS quality then positively affect both the user’s Usage Attitude and Trust, while Usage Attitude boosts User Satisfaction, all of which increases the user’s continued usage intention. However, Perceived Usefulness yields a stronger impact on Usage Attitude than Recommendation Quality and Perceived Ease of Use, indicating that the system’s practical utility yields more impact on user perception than usability or technical quality. Future RS development should focus on increasing long-term use by improving customer satisfaction through increased system usability and RS accuracy, supported to a lesser extent by features that bolster user trust and familiarity. These findings offer insight on optimizing RS designs and fostering continued engagement in Indonesia’s e-commerce landscape.