Privacy-aware cross-cloud service recommendations based on Boolean historical invocation records

Abstract

In the age of big data, service recommendation has provided an effective manner to filter valuable information from massive data. Generally, by observing the past service invocation records (Boolean values) distributed across different cloud platforms, a recommender system can infer personalized preferences of a user and recommend him/her new services to gain more profits. However, the historical service invocation records are a kind of private information for users. Therefore, how to protect sensitive user data distributed across multiple cloud platforms is becoming a necessity for successful service recommendations. Additionally, the historical service invocation records often update with time, which call for an efficient and scalable service recommendation method. In view of these challenges, we introduce the multi-probe Simhash technique in information retrieval domain into the recommendation process and further put forward a privacy-preserving recommendation method based on historical service invocation records. At last, we design several experiments on the real-world service quality data in set WS-DREAM. Experimental results show the feasibility of the proposal in terms of producing accurate recommended results while protecting users' private information contained in historical service invocation records.

QoS-Aware Web Services Recommendations Using Dynamic Clustering Algorithms

“…The presentation of the planned QoS mindful web service recommendation framework with DCLUS is contrasted and the current recommendation calculations by Wei et al (2019), like Arbitrary WS_DREAM, NDL (neighborhood-mindful profound learning), DCLUS Insightful Neuro-Fluffy Collective Sifting (INFCF) as evaluated by Anithadevi and Sundarambal (2019), dependent on accuracy, review, and F1 which is appeared in Table 1, 2 and 3 Here 10, 15, 25, 50 are four diverse web services handling test informational index taken at three unique occasions with 30 days time span for testing the calculations. The graphical portrayal of recommender calculations execution correlation is represented in fig 2, 4, and 5.…”

“…Then the result of each step of combination is improved by choosing a certain number of suitable services which are measured by utility values and characteristics. Wei et al (2019), here author presented the verifiable service conjuring records frequently update with time, which requires a proficient and adaptable service recommendation technique. They present the multi-test Simhash system in the in-sequence recuperation space into the recommendation cycle and further put forth an assurance shielding recommendation strategy reliant on true service conjuring records.…”