Optimizing Service Enterprise Marketing Policies using Supervised Attention Multi-Scale Temporal Convolutional Network

While scientific and technical advancements have increased consumer knowledge, existing market economic models are rapidly deteriorating due to these same issues. To adapt to changing customer demographics in the digital age, marketing tactics must be constantly updated and optimized. In this Manuscript, Optimizing Service Enterprise Marketing Policies using Supervised Attention Multi-Scale Temporal Convolutional Network (SEMP-SAMSTCN) is proposed. Initially, the data gathered from dataset Marketing Analytics dataset. Collected data are pre-processed to Handling missing values and data cleaning using Pseudo linear Maximum Correntropy Kalman Filter (PMCKF).Later, pre-processed image are given to SAMSTCN for effectively predict the sales. In general, SAMSTCN predicts does not express adapting optimization strategies to determine optimal parameters to ensure accurate data prediction. Hence, proposed utilize Adaptive Lightning Attachment Procedure Optimizer (ALAPO) enhance Efficient Predefined SAMSTCN accurately predict the sales. Then, the SEMP-SA-MSTCN is implemented to Python and the performance metrics such as, accuracy, precision and recall. Finally, the performance of SEMP-SA-MSTCN method provides 20.47%, 24.35%, and 276.78% high accuracy, 19.57%, 25.45%, and 29.75% higher Precision and 18.55%, 23.35%, and 27.63%higher recall while compared with existing Marketing Policy In Service Enterprises Using Deep Learning Model (MPISE-DNN), Lightweight deep learning model for marketing strategy optimization and characteristic analysis (LW-MSO-DCNN) and Evaluating cross-selling opportunities with recurrent neural networks on retail marketing (ECSO-RM-RNN) respectively.