Purchase Intent Prediction Using Session Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Website owners face challenges in determining the success of their websites, including whether user informational needs are met and whether users are purchasing advertised goods and services, as existing methods lack effective analytics for anonymous user behavior and purchase intent prediction.
Innovation Solution
An experience analytics system that analyzes anonymous user behavior on retail websites using machine learning models to predict purchase intent, combining session data with conversion information to identify missed purchase segments and provide real-time intent predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to analyze anonymous user behavior and predict purchase intent, then user intention understanding and conversion rate improvement are enhanced, but system complexity and data processing requirements increase
Solution Approach 1:
The patent segments user sessions into distinct analytical units with specific features (page views, time on site, interaction patterns). By dividing the complex analysis task into manageable session-level segments, the system can apply machine learning models to individual sessions rather than attempting to analyze all user behavior simultaneously, reducing overall system complexity while maintaining prediction accuracy.
Solution Approach 2:
The patent introduces session data as an intermediary layer between raw user behavior and purchase intent predictions. Session data aggregates and structures user interactions into meaningful features that serve as inputs for machine learning models, acting as a mediator that simplifies the complexity of directly analyzing raw behavioral data while preserving the information needed for accurate predictions.
2Loss of information
If session data is collected and analyzed for all users, then purchase intent prediction capability improves, but data storage and processing requirements increase
Solution Approach 1:
The patent extracts only the most relevant features from complete session data, such as key interaction patterns, time metrics, and navigation behaviors. Instead of storing and processing all raw user data, the system identifies and extracts the essential information needed for purchase intent prediction, reducing data volume while maintaining predictive accuracy by focusing on the most informative aspects of user behavior.
Solution Approach 2:
The patent applies partial action by analyzing only the specific session features that are most predictive of purchase intent, rather than processing all possible user behavior data. The system selectively processes relevant session attributes (such as pages viewed, time spent, interaction types) while ignoring less relevant information, thereby reducing data processing requirements while maintaining effective prediction capability.
Data Source
AI summary
The subject technology receives session data from a set of users associated with a retail website. The subject technology generates, using at least one machine learning model, a purchase intent prediction based at least in part on the session data. The subject technology determines a set of sessions that correspond to conversions on the retail website based on the session data. The subject technology generates a combination of data using first data from the purchase intent prediction with second data based on the set of sessions that correspond to conversions. The subject technology generates information related to a missed purchase segment based at least in part on the combination of data. The subject technology provides the information for display on a client device.