Predictive Assessment of Customer Behavior using Big Data Analytics

Abstract

A thorough understanding of online customer s purchase behavior will directly boost e-commerce business newlineperformance. Existing studies have overtly focused on purchase intention and used sales rank as a natural newlineproxy, which however has limited business application. Additionally, intention to purchase does not newlinenecessarily convert to actual retail purchases. newlineThis work started by analysing financial data set and designed a machine learning-based model to evaluate newlinethe credit risk for a particular borrower depending upon several relevant attributes. Two different approaches newlinebased upon decision tree and K-Nearest Neighbour have been proposed to evaluate credit risks. After moved newlinefurther to improve understanding of online customer s purchase behavior for an ecommerce platform by newlinepredicting the same using deep learning techniques. This study presented a deep learning model, developed newlinefor statistical tests, statistical analysis using correlation and association testing are performed. The ordinary newlinedimension reduction with principal component analysis and module eigenvalues, followed by a second newlinenormalization phase that maximizes the coefficient s size using possible values. The Keras library was used newlineon the third layer of the deep learning classification hierarchy with the rectified linear unit and sigmoid newlineactivation functions. newlineFurther compared the predictive capability of proposed deep learning method with other developed models. newlineThe results concluded that the deep learning technique outperformed the machine learning techniques when newlineapplied to the same dataset. These analyses will help platform designers plan for more platform engagements newlinewhile simultaneously expanding the academic understanding of purchase prediction for online e-commerce newlineplatforms