Application Recommendations with Continual Learning based on traffic classification

What is it about?

This paper proposes A DQN-based traffic classification method for application recommendation with continual learning. Its core idea is to embed a traffic classification model on the end, continuously detect user behavior, build user preference service ranking, and provide true and accurate user feedback data for application recommendation. In this paper, reinforcement learning technology is used to fine-tune the traffic classification model by setting the reward and punishment mechanism, which ensures the accuracy and timeliness of the traffic classification model. In this paper, experimental verification is carried out on ISCX and private data sets. The results show that this method has high accuracy and can effectively carry out continuous learning.

Featured Image

Photo by William Hook on Unsplash

Photo by William Hook on Unsplash

Why is it important?

With the popularity and development of smartphones, many mobile applications of various types have emerged. How to recommend mobile applications that match the user’s preferences and usage habits among the massive applications is a problem that needs to be solved. Traditional mobile application recommendation methods cannot dynamically track user behavior and preference changes in time and cannot timely correct the recommendation model, resulting in poor recommendation effects. The continual update of mobile applications will also invalidate the recommendation model based on traffic classification.

Perspectives