Multi-feature Search–based Purchasing Tendency Community Classification For Densely Distributed Clients In E-commerce

• Author(s):

  M.GughanRaja | M.SanjayKumar | A.AzimSaleh | S.PayasJenner | K.KabilDoss

• Keywords:

  AI, E-commerce, Purchasing Tendency, Com-munity Classification, Graph Neural Networks (GNN), Sequential Recommendation, Demand Forecasting, Marketplace Intelligence

• Abstract:

  Purchasing Tendency Is Defined As Customer Prefer-ences For Products And Brands, Interested In Price And Frequency Of Purchase, And Is Determined By Demographic, Transactional And Behavioral Attributes. In Today’s E-commerce, These Insights Are Critical For Recommendations And Managing Demand. But Conventional If-then Rules And Elementary Collaborative Filtering Approaches Lack Sophisticated Insights Into Interactions Between Customers, Products, And Locations, And The Demand At Different Times. To Overcome These Challenges, This Article Proposes A Community Classification System Of Clients Purchasing Inventory Using A Holistic Deep Learning Approach. Graph Neural Networks (GNNs) Capture The Relationship Between Customers, Products, And Regions, Facilitating Precise Identification Of Customer Com-munities And Region-based Demand (high, Emerging, Low). The SASRec Transformer-based Model Also Leverages Temporal In-formation About Customer Preferences By Training On Temporal Sequences, Capturing Both Short- And Long-term Information. This Approach Incorporates Demographic, Transactional And Be-havioral Data To Offer Insights To Sellers And Recommendations To Customers, Thus Improving Decision-making, Forecasting, And Efficiency In The Market.

---

Other Details

• Paper id:

  IJSARTV12I4105216

• Published in:

  Volume: 12 Issue: 4 April 2026

• Publication Date:

  2026-04-30

Download Article