Ordering Interface Grouping Items by Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online systems face challenges in helping customers efficiently find items they are interested in purchasing due to unrelated items being presented together, leading to decreased customer engagement and potential loss of orders.
Innovation Solution
An online system generates an ordering interface based on a category-based ranking of previously ordered items and an item-based ranking of replacement items, using machine learning to predict item availability and user preferences, thereby organizing items in a more relevant and accessible manner.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If items are arranged in ordering interface based on paid search results, promotions, or popularity, then commercial objectives are met, but customer efficiency in finding related items deteriorates
Solution Approach 1:
The ordering interface is segmented into multiple sections: a first section displaying previously ordered items and a second section displaying similar items. This segmentation allows customers to efficiently find related items in the first section while maintaining commercial objectives through the second section, thereby resolving the contradiction between search efficiency and commercial goals.
Solution Approach 2:
The system performs preliminary actions by pre-organizing items into categories (previously ordered items and similar items) before customer interaction. This pre-arrangement enables customers to quickly locate related items without scrolling through unrelated content, improving search efficiency while maintaining commercial positioning.
2Adaptability or versatility
If unrelated items are presented close to each other in ordering interface, then commercial positioning is achieved, but customer engagement deteriorates
Solution Approach 1:
Different regions of the ordering interface are assigned different qualities/functions: the first section displays previously ordered items for efficient retrieval, while the second section displays similar items for discovery. This local differentiation maintains interface flexibility while enhancing customer engagement through relevant item presentation.
3Device complexity
If customers scroll through multiple unrelated items to find desired items, then interface simplicity is maintained, but time consumption increases
Solution Approach 1:
The interface is segmented into distinct sections (previously ordered items and similar items) that are visually separated and logically organized. This segmentation reduces the need for scrolling through unrelated items while maintaining interface simplicity, thereby reducing search time without increasing structural complexity.
Data Source
AI summary
An online system receives a request from a user to access an ordering interface for a retailer and identifies a retailer location based on the user's location. The system uses a machine learning model to predict availabilities of items at the retailer location and identifies anchor items the user previously ordered from the retailer that are likely available. The system computes a first score for each anchor item based on an expected value associated with it and/or a likelihood the user will re-order it, determines categories associated with the anchor items, and ranks the categories based on the first score. For each category, the system identifies associated candidate items likely to be available and ranks them based on a second score for each candidate item computed based on a probability of user satisfaction with it as an anchor item replacement. The ordering interface is then generated based on the rankings.