A Personalized QoS Prediction Method for Web Services via Blockchain-Based Matrix Factorization

Abstract

Personalized quality of service (QoS) prediction plays an important role in helping users build high-quality service-oriented systems. To obtain accurate prediction results, many approaches have been investigated in recent years. However, these approaches do not fully address untrustworthy QoS values submitted by unreliable users, leading to inaccurate predictions. To address this issue, inspired by blockchain with distributed ledger technology, distributed consensus mechanisms, encryption algorithms, etc., we propose a personalized QoS prediction method for web services that we call blockchain-based matrix factorization (BMF). We develop a user verification approach based on homomorphic hash, and use the Byzantine agreement to remove unreliable users. Then, matrix factorization is employed to improve the accuracy of predictions and we evaluate the proposed BMF on a real-world web services dataset. Experimental results show that the proposed method significantly outperforms existing approaches, making it much more effective than traditional techniques.

Basketball Player's Value Evaluation by a Networks-based Variant Parameter Hidden Markov Model

“…The top row is the result of the real observation, and the bottom row is the result of our algorithm. By comparing and analyzing the data from the four groups (see Fig 3), it can be observed that deviation of the parameters is in the acceptable range [31]. In our experiment, we carefully compared all the game parameters of different teams in the 2016 and 2017 NBA Finals.…”

When Services Computing Meets Blockchain: Challenges and Opportunities

“…Combining credits of privacy-preservation of blockchain, Li et al [65] proposed a blockchain-based QoS-aware web services recommendation framework. At the same time, Cai et al [64] proposed a personalized blockchain-based prediction approach. Both of them are the variants of matrix factorization.…”

An improved X-means and isolation forest based methodology for network traffic anomaly detection

“…In recent years, the network environment has become increasingly complex. Traffic data have exploded and mass infrastructure based on internet of things (IoT) technology and complex networks has had a significant impact on society and the economy [ 1 – 3 ]. Due to the increase in Internet services, network abnormalities including malicious attacks and poor quality of network services have become more diversified and substantially affecting the operation of web services and causing social and economic losses [ 4 – 7 ].…”