Mathematical Exploration of B2C Electronic Commerce architecture via Back propagation Network Learning Algorithm

The present study assesses the technique of back propagation neural networks to appraise the average response time of B2C Electronic Commerce architecture. In order to delineate the response time, diverse array of user requests were engaged per unit time. Furthermore, engagement of Back Propagation Network Learning (BPNL) algorithm is used to summarize the average response time and augment the enactment of the system. The comprehensive study does the comparative investigation to express the average response time for ANN enabled and without-ANN-enabled algorithm. The objective was to plaid whether ANN enabled algorithm had any bearing on the overall performance of the system. For BPNL algorithm, learning of the responses for the user requests were steered for 7 repetitions and then thorough phases were accomplished to assess the response time. After each iterations, error rates were dogged and then feed forward and back propagation algorithm were used to improve the performance. The experimentation will find its prominence in imminent B2C Electronic Commerce system project and employment and will convey the outline for such investigation. Finally, the study expands the meticulous inferences of the study.