Fulfillment Source Slot Allocation Using Interaction and Discovery Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online systems limit the number of sources displayed to users with limited display areas, relying on prior interactions to select sources, which reduces the likelihood of users interacting with a broader range of sources and limits exposure to new sources.
Innovation Solution
An online system uses a combination of interaction and discovery models to allocate slots in a source identification section, balancing display of sources the user has previously interacted with and new sources, optimizing the limited display area by accounting for user interaction patterns and geographic region-specific sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the number of sources displayed in the source identification section is limited to optimize display area, then the display area utilization is improved, but the user's exposure to new sources is reduced
Solution Approach 1:
The source identification section is divided into multiple slots, each capable of displaying different types of sources (familiar sources vs. new sources). This segmentation allows the limited display area to be strategically allocated between reinforcing user preferences and introducing new sources, resolving the contradiction between maximizing display area utilization and ensuring diverse source exposure.
Solution Approach 2:
Different slots within the source identification section are assigned different qualities or characteristics - some slots display sources based on user interaction history (familiar sources) while others display new sources. This local differentiation allows the limited display area to simultaneously serve multiple functions: reinforcing user preferences and expanding source diversity.
2Ease of operation
If only sources with which the user has previously interacted are displayed, then the likelihood of user interaction with displayed sources is improved, but the ability to identify new sources to the user is reduced
Solution Approach 1:
The source identification section is segmented into different functional zones: slots for familiar sources (based on interaction history) and slots for new sources. This segmentation enables the system to simultaneously leverage user's prior interactions to maintain ease of operation while introducing new sources to expand adaptability and versatility.
Solution Approach 2:
The system dynamically adjusts the parameters of source selection by using different models (interaction model vs. discovery model) for different slots. The interaction model prioritizes sources with high user interaction probability, while the discovery model prioritizes new sources, allowing the system to balance ease of operation with new source identification based on configurable parameters.
3Device complexity
If a single model is used to select sources for all slots, then the system complexity is reduced, but the optimization of source selection for different display purposes is limited
Solution Approach 1:
The source selection process is segmented by applying different models (interaction model and discovery model) to different slots based on their specific purposes. This segmentation allows each model to be optimized for its specific function while maintaining overall system manageability, improving source selection optimization without excessive complexity.
Solution Approach 2:
The system employs a multi-functional approach where a single source identification section serves multiple purposes through different slots: reinforcing user preferences, introducing new sources, and maintaining system simplicity. This universality allows the system to achieve optimized source selection for different display purposes while managing complexity through unified interface design.
Data Source
AI summary
An online system displays an interface to users including slots in which sources from a list of sources of items (e.g., physical items, content items) are presented. The user may select a source via the interface to view items provided by, or associated with, the source. To simplify a user identifying a desired source, the online system includes sources that a user is likely to select as well as new sources in the list. To balance the competing interests of relevance of sources with which the user previously interacted and discovery of new sources, the online system selects an allocation of slots for new sources and for sources with prior interaction based on interactions by users in the geographic regions with different allocations of slots. Based on the selected allocation of slots, the online system selects specific retailers for each slot using ranking models corresponding to different slots.


