Event-Based Product Recommendation System for Online Marketplaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Consumers face difficulty in finding and learning about products of interest due to the overwhelming number of options available in online marketplaces, where events like news events, product releases, or holidays create surges in public interest but are not effectively leveraged to promote related products.

Innovation Solution

A system and method within an Internet marketplace that identifies events, associates them with products, and recommends relevant merchandise to shoppers using a combination of automatic and manual event identification, product databases, and collaborative filtering, providing links to news stories and product listings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple products are offered to meet consumer needs, then product availability increases, but the task of finding a product of interest becomes more daunting

Engineering Contradiction:
Improveproduct availabilityVSAvoidproduct search difficulty
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent introduces an event-based recommendation system that acts as an intermediary between consumers and the vast product catalog. By using events (news events, product releases, holidays) as mediators, the system automatically identifies and presents relevant products to consumers without requiring them to manually search through numerous options. This resolves the contradiction by maintaining high product availability while simplifying the search process through event-driven curation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary action by proactively identifying events and pre-selecting relevant products before consumers need to search. The automated event identification and product recommendation processes occur in advance, preparing personalized product lists based on upcoming or current events. This eliminates the need for consumers to manually browse through available products, thereby reducing search difficulty while maintaining comprehensive product availability.

Inventive Principle:
Principle #10Preliminary action

2Loss of information

If events are leveraged to promote related products, then consumer discovery of relevant products improves, but system complexity increases

Engineering Contradiction:
Improveproduct discovery effectivenessVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the complex task of product recommendation into distinct modular components: event identification module, event-product association module, and recommendation generation module. Each module handles a specific aspect of the process independently, making the overall system more manageable despite its complexity. The event identification module monitors for events, the association module links events to relevant products, and the recommendation module presents products to consumers, thereby improving product discovery while organizing system complexity into manageable segments.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9928525B2Method, medium, and system for promoting items based on event information
Publication Date: 2018.03.27 EBAY INC
  • US9928525B2 patent drawing
  • US9928525B2 patent drawing
  • US9928525B2 patent drawing

AI summary

Various embodiments are described herein that provide one or more of a systems, methods, software, and data structures within an Internet marketplace context that are useful to promote products that may be associated with an event occurrence. Some embodiments further utilize collaborative filtering to augment event-based product recommendations.