Predictive Model for Online Cart Session End Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the end of an online shopping cart session are inadequate, as they rely on fixed time intervals, which do not account for individual customer behavior, leading to potential customer dissatisfaction and inappropriate retargeting.
Innovation Solution
An analytics application uses a predictive model based on user and session features to identify the last user click input associated with an online cart session, predicting when the session has ended, allowing for targeted retargeting notifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed time interval (e.g., 30 minutes) is used to determine session end, then the method is simple to implement, but it creates customer dissatisfaction and inappropriate retargeting by not accounting for individual customer behavior patterns
Solution Approach 1:
The patent changes the parameter from a fixed time interval to a dynamic prediction model that uses multiple features (time since last click, session duration, user behavior patterns) to determine session end. This allows the system to adapt to individual customer behavior patterns while maintaining implementation simplicity through automated predictive algorithms.
Solution Approach 2:
The patent replaces the mechanical/simple time-based system with an intelligent predictive model that uses machine learning algorithms to analyze user behavior patterns. This substitution enables more accurate session end determination without significantly increasing operational complexity, as the prediction model processes data automatically.
2Use of energy by moving object
If a fixed time interval is used to determine session end, then the system requires minimal computational resources, but it leads to unnecessary follow-up communications and poor user experience
Solution Approach 1:
The predictive model performs self-service by automatically analyzing user behavior patterns and determining session end without requiring manual intervention or complex computational processing for each individual case. The system uses pre-trained models that efficiently process input features to generate predictions, reducing the need for resource-intensive analysis while improving accuracy.
3Reliability
If the system waits for explicit customer indication of session end, then customer experience is improved, but the marketer cannot send timely reminder emails or communications
Solution Approach 1:
The predictive model performs preliminary action by predicting session end before the customer explicitly indicates it. By analyzing behavior patterns in advance, the system can proactively determine when a session has likely ended and trigger timely follow-up communications, eliminating the time delay associated with waiting for explicit customer signals.
Data Source
AI summary
In embodiments of identifying the end of an on-line cart session, an analytics application captures user click inputs on pages of a Web site, where the user click inputs include adding one or more items for purchase to an on-line cart associated with the Web site. The analytics application then utilizes a predictive model, as well as user and session features of the on-line cart session, to predict whether a previous user click input is the last user click input associated with the on-line cart session, indicating an end of the session. A notification can then be provided that the on-line cart session has ended based on the prediction of the last user click input associated with the on-line cart session. The analytics application or the marketer can then retarget a user associated with the on-line cart session, such as with a message pertaining to the on-line cart session.