Design and development of the recommendation mechanism with performance high and scalable using Kafka, Spring Boot and algorithms collaborative filtering
Session
Computer Science and Communication Engineering
Description
Recommender systems have become an indispensable part of human daily life due to the large amount of information where in this case information filtering must be implemented that limits the capabilities of the recommender system and improving the user experience by helping users to get what they themselves want. The goal of this implementation is the recommendation mechanis that is extremely efficient and scalable, this document includes details about the integration of Kafka,Spring Boot and collaborative filtering algorithms in the recommendation mechanism. This integration shows the latest model of the recommender mechanism that aims to provide recommendations as personalized and accurate as possible. With this combination of high techonologies it creates a modern mechanism designed to provide personalized recommendations to users effectively.The current state of technology has brought significant changes in the way users interact with the system, leading to the need for systems more advanced recommendations. These systems use interactivity and user preferences to create personalized suggestions, improving the user experience across different platforms. To meet this requirement, the integration of Kafka,Spring Boot and collaborative filtering algorithms is the most compact, fast and powerful solution to meet the needs of the advanced recommendation mechanism.Kafka, serving as a distributed streaming platform, is the focal point of the application architecture facilitating real-time data collection and distribution.Kafka’s ability to scale and asynchronize the system effectively makes it suitable for managing large amounts of data and user interactions. Spring Boot on the other hand is a powerful framework for developing applications and complements Kafka by enabling the rapid creation of microservices with the modular structure and automation also increases the flexibility and ease of maintenance of the recommendation system. Within the application, with the implementation of collaborative filtering algorithms, interactions are examined to discover connections and similarities between users and items with the use of techniques such as matrix factorization or nearest neighbor methods, accurate recommendations are provided. By combining these technologies, the recommendation mechanism with high performance and scalability is achieved.
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-95-6
Location
UBT Lipjan, Kosovo
Start Date
28-10-2023 8:00 AM
End Date
29-10-2023 6:00 PM
DOI
10.33107/ubt-ic.2023.294
Recommended Citation
Jajaga, Edmond, "Design and development of the recommendation mechanism with performance high and scalable using Kafka, Spring Boot and algorithms collaborative filtering" (2023). UBT International Conference. 30.
https://knowledgecenter.ubt-uni.net/conference/IC/CS/30
Design and development of the recommendation mechanism with performance high and scalable using Kafka, Spring Boot and algorithms collaborative filtering
UBT Lipjan, Kosovo
Recommender systems have become an indispensable part of human daily life due to the large amount of information where in this case information filtering must be implemented that limits the capabilities of the recommender system and improving the user experience by helping users to get what they themselves want. The goal of this implementation is the recommendation mechanis that is extremely efficient and scalable, this document includes details about the integration of Kafka,Spring Boot and collaborative filtering algorithms in the recommendation mechanism. This integration shows the latest model of the recommender mechanism that aims to provide recommendations as personalized and accurate as possible. With this combination of high techonologies it creates a modern mechanism designed to provide personalized recommendations to users effectively.The current state of technology has brought significant changes in the way users interact with the system, leading to the need for systems more advanced recommendations. These systems use interactivity and user preferences to create personalized suggestions, improving the user experience across different platforms. To meet this requirement, the integration of Kafka,Spring Boot and collaborative filtering algorithms is the most compact, fast and powerful solution to meet the needs of the advanced recommendation mechanism.Kafka, serving as a distributed streaming platform, is the focal point of the application architecture facilitating real-time data collection and distribution.Kafka’s ability to scale and asynchronize the system effectively makes it suitable for managing large amounts of data and user interactions. Spring Boot on the other hand is a powerful framework for developing applications and complements Kafka by enabling the rapid creation of microservices with the modular structure and automation also increases the flexibility and ease of maintenance of the recommendation system. Within the application, with the implementation of collaborative filtering algorithms, interactions are examined to discover connections and similarities between users and items with the use of techniques such as matrix factorization or nearest neighbor methods, accurate recommendations are provided. By combining these technologies, the recommendation mechanism with high performance and scalability is achieved.