MAPLE: Mobile App Prediction Leveraging Large Language Model Embeddings. (arXiv:2309.08648v2 [cs.CL] UPDATED)

In recent years, predicting mobile app usage has become increasingly
important for areas like app recommendation, user behaviour analysis, and
mobile resource management. Existing models, however, struggle with the
heterogeneous nature of contextual data and the user cold start problem. This
study introduces a novel prediction model, Mobile App Prediction Leveraging
Large Language Model Embeddings (MAPLE), which employs Large Language Models
(LLMs) and installed app similarity to overcome these challenges. MAPLE
utilises the power of LLMs to process contextual data …

analysis app arxiv become cold start cs.cl data embeddings language language model large language large language model management mobile mobile app nature novel prediction recommendation struggle study usage