New distributed-topsis approach for multi-criteria decision-making problems in a big data context

Abstract Nowadays, the online environment is extra information-rich and allows companies to offer receive more options opportunities in multiple areas. Thus, decision-makers have abundantly available alternatives choose from best one or rank most least preferred. However, multicriteria decision-making field, tools support a limited number of with as narrow criteria possible. Decision-makers are forced apply screening filtering method reduce size problem, which will slow down process eliminate some potential rest process. Implementing MCDM methods high-performance parallel distributed computing environments becomes crucial ensure scalability solutions Big Data contexts, where can consider vast alternatives, each being described on basis criteria. In this context, we TOPSIS widely used methods. We present implementation based MapReduce paradigm. This solution response time facilitate analysis robustness sensitivity high-dimension problem at reasonable time. Three problems were evaluated show proposed approach's computational efficiency performance. All experiments carried out within GCP's Dataproc, service allowing execution Apache Hadoop Spark tasks Google Cloud. The results tests obtained very significant promising.