Enhanced Item Recommendation via Graph Properties in Sparse Data

ÖZER Ş. D. İ., ORMAN G. K.

20th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2024, Corfu, Yunanistan, 27 - 30 Haziran 2024, cilt.714, ss.111-124 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 714
  • Doi Numarası: 10.1007/978-3-031-63223-5_9
  • Basıldığı Şehir: Corfu
  • Basıldığı Ülke: Yunanistan
  • Sayfa Sayıları: ss.111-124
  • Anahtar Kelimeler: bipartite networks, negative sampling, power-law distribution, Recommender system, sparsity
  • Galatasaray Üniversitesi Adresli: Evet

Özet

Item recommendation for users is a salient feature of many transaction-based systems. Finding the most appropriate items is crucial for both marketing and analytical perspectives. The latest works focus on ranking-based personalized recommenders. However, they recommend the same number of items for everyone and still suffer from the interaction sparsity issue. We propose a complex-graph-oriented supervised learning-based link prediction with a realistic negative sampling application for overcoming these problems. We employ the power-law degree distribution property of the complex graphs to sample the negative instances. The experiments show that our method outperforms ranking-based personalized recommenders with a 20% increase in recommendation success in multiple evaluation metrics.