Optimization of cross-border e-commerce marketing strategy based on deep learning model

Abstract

Abstract The advent of the era of artificial intelligence provides technical support for cross-border e-commerce marketing to break the traditional competitive model and make efforts to build an online shopping platform that can meet international sellers’ and consumers’ transactions at any time around the world. This paper constructs a cross-border e-commerce marketing strategy optimization model based on deep reinforcement learning and convolutional neural network under artificial intelligence technology and explores the optimization method of the cross-border e-commerce marketing strategy by verifying the accuracy of the model and mining and analyzing the example data of Company A’s cross-border e-commerce platform. From the data, the accuracy of the deep convolutional neural network model is 99.47%, the proportion of beauty and beauty, mother and child care, and medical and health products in the product marketing strategy is 79.92%, 71.48%, and 59.93%, respectively, and the proportion of search traffic of the top three keywords in the search channel marketing is 42.69%, 31.23%, and 22.65%, respectively, and the ranking of the bottom The average traffic search of the seven types of keywords is less than 10%. This also shows that the optimization of a cross-border e-commerce marketing strategy based on the deep convolutional neural network can clearly analyze the data in the current marketing strategy, guide how to optimize the marketing strategy based on the data, and then improve the economic benefits of cross-border e-commerce enterprises. Applying a deep convolutional neural network model in a cross-border e-commerce marketing strategy also provides a direction for the new development field of artificial intelligence technology, which is beneficial to the further development of artificial intelligence technology.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 5 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.