MIAE: A Mobile Application Recommendation Method Based on a NTK Model

The emergence of more and more mobile applications in recent years has driven the development of application recommendation algorithms. However, many algorithms are limited to using users’ ratings for apps while considering other relevant information as marginal. In this paper, we consider the user’s app usage time and the user’s forum level in addition to the rating, explore the impact of different attributes and multidimensional attributes on the recommendation algorithms, and propose a model MIAE (Multi-info. Autoencoders for Recommendation) based on a Neural Tangent Kernel(NTK) that can accommodate multiple information dimensions. Specifically, our approach involves utilizing a fully-connected neural network with NTK parameterization. We introduce ridge regression as a regularization technique to convert the recommendation problem into a probabilistic framework. To obtain results, we employ a gradient descent method based on the NTK, enabling efficient optimization. We tested our approach using both comparison experiment and ablation experiment. In the comparison experiment, we used two representative algorithms, GLocal-K [1] and CosRec [2], as baselines. Quantitative results on our crawled taptap dataset show that our proposed NTK-based approach, MIAE, with one-dimensional information input outperforms representative algorithms, achieving high performance on various evaluation metrics. In our ablation experiment, we examined several variables, including the user’s rating of the app, app usage duration, and forum level. The results demonstrated that utilizing the individual variable ‘Level’ led to the highest recall and F1 scores. On the other hand, employing a combination of variables such as ‘Level + Duration’ resulted in the best precision and NDCG scores. This finding confirms the beneficial impact of both the user’s app usage duration and level on app recommendations.