Gift Item Ranking Using ML Giftability Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online concierge systems struggle to suggest appropriate gift items due to the wide variety of products available, as items like chocolate chips or basic household items may not be suitable for gifting, despite being frequently purchased by customers.
Innovation Solution
An online concierge system uses a machine learning model to predict a giftability score for items based on customer profiles and item attributes, computing a composite score for each candidate item to determine its appropriateness as a gift, and ranks and selects items for gifting accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the system suggests items based on customer purchase history and favorite items, then the suggestions are personalized to customer preferences, but the suggested items may not be appropriate for gifting (e.g., chocolate chips, basic household items)
Solution Approach 1:
The system segments the item evaluation process into multiple independent components: customer preference matching, giftability scoring, and composite score calculation. Each component handles a specific aspect of gift suitability, allowing the system to maintain personalization while ensuring appropriateness through separate evaluation criteria.
Solution Approach 2:
The system introduces a new parameter dimension (giftability score) to the existing customer preference matching. By combining multiple parameters (customer affinity, giftability, popularity) into a composite score, the system transforms the suggestion quality from single-criterion to multi-criterion evaluation, resolving the contradiction between personalization and appropriateness.
2Adaptability or versatility
If the system allows customers to order a wide variety of items from various retailers, then the system offers high product diversity and selection, but items suggested as gifts may not be suitable (e.g., groceries, basic household items)
Solution Approach 1:
The giftability score acts as an intermediary filter between the broad product catalog and gift suggestions. This intermediary layer evaluates items based on gift-appropriateness criteria, allowing the system to maintain access to diverse products while ensuring only suitable items are recommended for gifting.
Solution Approach 2:
The system performs preliminary filtering of items based on giftability scores before presenting suggestions to customers. By pre-evaluating item suitability and computing composite scores that incorporate gift appropriateness, the system prepares appropriate recommendations in advance, ensuring gift suitability is maintained across the diverse product catalog.
Data Source
AI summary
An online concierge system receives a request to purchase a gift for a user of the system and retrieves a profile associated with the user. Based on the profile and attributes of items included among inventories of one or more retailer locations, the system identifies a set of candidate items for which the user is likely to have an affinity. The system accesses a machine learning model trained to predict a giftability score for an item and applies the model to attributes of each candidate item to predict its giftability score. Based on its giftability score and the profile, the system computes a composite score for each candidate item indicating an appropriateness of gifting the candidate item to the user. The system ranks the set of candidate items based on the composite scores and selects one or more suggested items for gifting to the user based on the ranking.