Mobile Application Usage Forecast Based on LSTM

The danger of cell phone addiction, a widespread phenomenon among young people, is that it can unconsciously take up a lot of time for study and work, causing worries about school and work. The existing methods to effectively improve this problem are usually pre-planning and post-analysis, relying on the user's self-control. We propose an LSTM-based neural network predictive classification method from the perspective of preventing problems before they occur. By mining the weeks-long application usage data information collected from users' cell phones, the historical data is classified as whether the timeout is over, and the LSTM network model is trained using these data sequences for learning, and after several rounds of training iterations to form a stable network, and a predictive judgment classification is performed in the test set for short-term future time. The performance of the network model is evaluated using the F1-score, a common judgment indicator in classification problems, and it is verified that the network can effectively learn the correlation between data sequences in a short period scenario and has a good prediction efficiency, thus providing a preventive solution to the problem of cell phone addiction that does not emphasize reliance on subjective self-control.