Supervised machine learning for document analysis and prediction

What if the data gets bigger and bigger? What if handling such huge amount of data started to be critically irritating and need much more attention? These questions became very concerning nowadays. Several organizations and industrial businesses are in need of information system and strategic organizational tool to easily handle huge data and learn the behavior of these data. In this study we proposed a model that is based on Supervised Machine learning to measure, evaluate and learn the similarity of attributes within documents. The documents are in the form of business plan executive summary that consist of several attributes that are used as parameters for evaluation. Results showed that by using similarity learning, attributes within the business plan documents are rated and furthermore the overall documents are ranked showing the effective correlation and association between attributes.