Big Data implementation in the tourism industry with the integration of Singular Value Decomposition (SVD)

Abstract

Big Service is an extremely important application of service computing to provide predictive and needed services to humans. On the other hand, Big Data as a Service can be achieved implementing by processing large chunk of data effectively. Volume, Velocity and Variety are distinct characteristics of large scale and heterogeneous data that includes unstructured, semi-structured and structured data. Since the arrival of big data, it is a great challenge to efficiently represent and process big data with a unified scheme. Moreover, amount of data including unstructured, semistructured, structured data in the tourism industry is increasing proportionally. This huge set of heterogeneous data needs to be processed and converted into a strategic approach to enhance and establish new methods for innovation and enhancement in the field of sustainable tourism. In our thesis we are aiming to find a efficient implantation of Big Data as a Service in the tourism industry and to give a good understanding of the advantages of Big Data in the tourism sector. In addition, in our thesis paper we propose Singular Value Decomposition (SVD) to process and optimize the heterogeneous data to minimize the memory usage. A unified tensor model is proposed to efficiently process the heterogeneous data using SVD incremental algorithms. With tensor extension various types of data are represented as sub-tensors and then are merged in a unified tensor. It is effective for big data representation and dimensionality reduction. The purpose of using the integration is to process and analyze the big data to discover behavioral patterns in tourism industry and propose an effective model to employ data in the tourism sector.