Parallel Selective Sampling for Imbalance Data Sports Activities

Abstract

Big data has a huge amount of large data set. Large data set has some major problems; the first one is size of the data and the second one is size of the data classes are strongly imbalanced. Several places where different devices produce the immense amount of data. Using this data nature, they are unable to determine the outcome from the data. To solve this problem, many numbers of applications and algorithms are used. Even though there are many applications and algorithms, many limitations occur while implementing the algorithm and using the applications. In the literature D’Addabbo and Maglietta [1] proposed a preprocessing technique method called parallel selective sampling (PSS). This preprocessing technique can be combined with any classification algorithm. In our research, we are combining PSS along with relevance vector machine (RVM). This PSS-RVM method provides the finest outcome and the existing Data Set algorithm for sporting activities.