Dynamic Display Scheduling for E-Commerce Product Sequencing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing merchandising strategies in electronic commerce systems fail to dynamically adapt to user inputs, leading to suboptimal product sequencing and reduced conversion rates, average order values, and increased returns.
Innovation Solution
A method and apparatus that determine a performance metric for display scheduling based on user inputs, compute a response performance score, and adjust the scheduling strategy if necessary, by changing parameters or switching to a different strategy, to optimize product sequencing and improve user engagement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed merchandising strategy is used for product sequencing, then the system is simple to implement, but conversion rates and average order values decrease due to inability to adapt to user behavior
Solution Approach 1:
The patent implements dynamic merchandising strategies that automatically adjust product sequencing based on real-time user behavior data. The system transitions from static pre-defined sequences to dynamic sequences that adapt to user interactions, browsing patterns, and preferences, thereby resolving the contradiction between adaptability and system complexity.
Solution Approach 2:
The system incorporates feedback loops where user behavior data is continuously collected, analyzed, and used to adjust merchandising strategies. This closed-loop feedback mechanism enables the system to learn from user interactions and optimize product sequencing dynamically, achieving adaptability while managing complexity through automated decision-making algorithms.
2Productivity
If product sequencing is optimized based on user behavior data, then conversion rates increase, but the system requires complex real-time data processing and analysis
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing user behavior data in structured formats before it is needed for sequencing decisions. Data is collected, cleaned, and organized in advance, allowing faster real-time processing when product sequencing decisions must be made, thus improving conversion rates without proportionally increasing processing complexity.
Solution Approach 2:
The patent introduces intermediary components such as data processing intermediaries and algorithmic mediators that bridge raw user behavior data and merchandising decisions. These intermediaries simplify the complexity by abstracting complex data processing into manageable layers, enabling high conversion rates through optimized sequencing without requiring the entire system to handle full data processing complexity.
3Productivity
If the system monitors and adjusts merchandising strategies in real-time, then average order values increase, but computational resources and processing time increase
Solution Approach 1:
The system applies partial monitoring and adjustment by focusing computational resources on key user behaviors and critical decision points rather than continuously analyzing all user interactions. This selective approach allows the system to increase average order values through targeted real-time adjustments while conserving computational resources by not processing every possible data point at full intensity.
4Reliability
If the system implements dynamic strategy changes based on performance scores, then returns decrease through better product matching, but the frequency of strategy changes increases system instability
Solution Approach 1:
The system implements periodic strategy changes rather than continuous adjustments. Performance scores are evaluated at defined intervals or after reaching specific thresholds, allowing the system to maintain stable strategies for extended periods while still achieving improved product matching accuracy. This periodic approach reduces strategy churn and system instability while maintaining high reliability in product recommendations.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Apparatuses and methods of controlling scheduling of displays presented in response to data indicative of user inputs from user terminals in a computerised system are disclosed. A performance metric is determined for a response by a data processing apparatus configured to respond to user terminals, the response being provided in accordance with a strategy of scheduling displays when responding to data indicative of at least one user input. A response performance score is computed based on the determined performance metric and a reference metric representative of a preferred result when responding data indicative of user inputs. It can then be determined, based on the response performance score, whether the strategy of scheduling displays when responding data indicative of user inputs needs a change.