Buyer to Seller Recommendation under Constraints

TL;DR

This paper introduces new constrained recommendation problems for matching buyers to sellers, addressing practical limitations and conflicts, and proposes efficient algorithms with real-world validation.

Contribution

It formulates the C-REC and CAC-REC problems, models C-REC with linear programming, proves CAC-REC NP-hardness, and develops approximation algorithms with experimental validation.

Findings

C-REC can be solved efficiently with linear programming.

CAC-REC is NP-hard, requiring approximation algorithms.

Proposed algorithms perform close to optimal on real datasets.

Abstract

The majority of recommender systems are designed to recommend items (such as movies and products) to users. We focus on the problem of recommending buyers to sellers which comes with new challenges: (1) constraints on the number of recommendations buyers are part of before they become overwhelmed, (2) constraints on the number of recommendations sellers receive within their budget, and (3) constraints on the set of buyers that sellers want to receive (e.g., no more than two people from the same household). We propose the following critical problems of recommending buyers to sellers: Constrained Recommendation (C-REC) capturing the first two challenges, and Conflict-Aware Constrained Recommendation (CAC-REC) capturing all three challenges at the same time. We show that C-REC can be modeled using linear programming and can be efficiently solved using modern solvers. On the other hand, we show that CAC-REC is NP-hard. We propose two approximate algorithms to solve CAC-REC and show that they achieve close to optimal solutions via comprehensive experiments using real-world datasets.