The Consumer Financial Protection Bureau is a federal agency responsible for protecting rights of retail consumers. The agency was established in USA for enabling the USA consumers to report complaint and support related information regarding their respective financial concerns with the federal government. The Consumer Complaint Database is a collection of complaints received by Consumer Finance Protection Bureau on a range of consumer financial products and services offered by banks and other financial institutions across the United States of America. There is no licensing associated with the data and is intended for public access and use. Each complaint consists of attributes that can uniquely describe and identify it. These features have been utilized for data analysis and predictions. In this paper we are using text classification techniques like Naïve Bayes, Decision Tree, Generalized Linear Model, Fast Large Margin, Deep learning and Support Vector Classifier in Rapid miner tool to classify the consumer complaints into respective product or service offered by the financial institutions. This information can be used in prescriptive analysis to enhance financial consumer services and improve the response quality of automated consumer support systems.