Aware Web Service Recommendation by Collaborative Filtering. (Domain: Web Service)

09. Aware Web Service Recommendation by Collaborative Filtering. (Domain: Web Service)

ABSTRACT:

With increasing presence and adoption of Web services on the World Wide Web, Quality-of-Service (QoS) is becoming important for describing nonfunctional characteristics of Web services. In this paper, we present a collaborative filtering approach for predicting QoS values of Web services and making Web service recommendation by taking advantages of past usage experiences of service users. We first propose a user-collaborative mechanism for past Web service QoS information collection from different service users. Then, based on the collected QoS data, a collaborative filtering approach is designed to predict Web service QoS values. Finally, a prototype called WSRec is implemented by Java language and deployed to the Internet for conducting real-world experiments. To study the QoS value prediction accuracy of our approach, 1.5 millions Web service invocation results are collected from 150 service users in 24 countries on 100 real-world Web services in 22 countries. The experimental results show that our algorithm achieves better prediction accuracy than other approaches. Our Web service QoS data set is publicly released for future research.

EXISTING SYSTEM:

• Client-side Web service evaluation requires real-world Web service invocations and encounters the following drawbacks:
• First, real-world Web service invocations impose costs for the service users and consume resources of the service providers. Some Web service invocations may even be charged.
• Second, there may exist too many Web service candidates to be evaluated and some suitable Web services may not be discovered and included in the evaluation list by the service users.
• Finally, most service users are not experts on Web service evaluation and the common time-to-market constraints limit an in-depth evaluation of the target Web services.

PROPOSED SYSTEM:

• Without sufficient client-side evaluation, accurate values of the user-dependent QoS properties cannot be obtained. Optimal Web service selection and recommendation are thus difficult to achieve.
• To attack this critical challenge, we propose a collaborative filtering based approach for making personalized QoS value prediction for the service users.
• Collaborative filtering is the method which automatically predicts values of the current user by collecting information from other similar users or items.
• Well-known collaborative filtering methods include user-based approaches and item-based approaches. Due to their great successes in modeling characteristics of users and items, collaborative filtering techniques have been widely employed in famous commercial systems, such as Amazon, Ebay, etc.
• In this paper, we systematically combine the user-based approach and item-based approach for predicting the QoS values for the current user by employing historical Web service QoS data from other similar users and similar Web services.

HARDWARE REQUIREMENTS

•                     SYSTEM                     : Pentium IV 2.4 GHz

•                     HARD DISK               : 40 GB

•                     MONITOR                  : 15 VGA colour

•                     MOUSE                      : Logitech.

•                     RAM                           : 256 MB

•                     KEYBOARD               : 110 keys enhanced.

SOFTWARE REQUIREMENTS

•                     Operating system          :           Windows XP Professional

•                     Front End                     :           JAVA

•                     Tool                             :           NETBEANS IDE

REFERENCE:

Zibin Zheng, Hao Ma, Michael R. Lyu and Irwin King, “QoS-Aware Web Service Recommendation by Collaborative Filtering”, IEEE Transactions on Services Computing, Vol.4, No.2, April-June 2011.