A Hierarchical Optimizer for Recommendation System Based on Shortest Path Algorithm
This addresses recommendation quality issues in geosocial networks, but appears incremental as it builds on existing shortest path methods.
The paper tackled the problem of unconvincing recommendations from shortest path algorithms in geosocial networks by designing a hierarchical optimizer with classifiers and a constant optimizer, resulting in optimized recommendations based on service provider features.
Top-k Nearest Geosocial Keyword (T-kNGK) query on geosocial network is defined to give users k recommendations based on some keywords and designated spatial range, and can be realized by shortest path algorithms. However, shortest path algorithm cannot provide convincing recommendations, so we design a hierarchical optimizer consisting of classifiers and a constant optimizer to optimize the result by some features of the service providers.