Association Rule Learning for App Transaction Trouble Spot Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing customer interactions in web or mobile applications are inefficient, as they require expensive and time-consuming replay of customer sessions to identify trouble spots, and lack the ability to quantify customer difficulties effectively, leading to revenue losses due to poor user experience.
Innovation Solution
An approach that utilizes an association rule learning algorithm, such as the Apriori algorithm, to generate rules based on customer transaction data, predicting user outcomes and identifying areas of difficulty by analyzing historical interactions and providing dynamic assistance to improve user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If customer session replay is used to identify trouble spots, then customer struggle points can be visualized, but the process becomes very expensive and time consuming
Solution Approach 1:
The system performs preliminary analysis by automatically processing customer session data through association rule learning algorithms to generate confidence values and identify trouble spots before any human review is needed. This preliminary action eliminates the need for manual replay and analysis, directly resolving the time loss issue while maintaining identification accuracy.
Solution Approach 2:
Instead of requiring analysts to replay actual customer sessions, the system creates a computational model (association rules with confidence values) that replicates the analysis function. This copying approach allows automated identification of trouble spots without the time-consuming manual replay process, while preserving the precision of trouble spot detection.
2Loss of information
If manual session replay is performed to see customer interactions, then specific struggle points can be identified, but the cost and time required increase significantly
Solution Approach 1:
The system enables self-service analysis where the data automatically generates association rules and confidence values without requiring human analysts to perform manual replay. The system serves itself by processing customer interaction data through automated algorithms, preserving detailed interaction information while eliminating the high resource consumption of manual analysis.
Solution Approach 2:
The patent replaces the mechanical process of manual session replay with an automated computational system using association rule learning algorithms. This substitution preserves all detailed interaction information through systematic processing while dramatically reducing the energy and resource consumption associated with human analysts manually reviewing sessions.
3Measurement precision
If traditional analysis methods are used to quantify customer difficulties, then some metrics can be obtained, but the ability to predict customer outcomes is insufficient
Solution Approach 1:
The system implements feedback by using association rule learning to analyze customer transaction patterns and generate confidence values that predict future customer outcomes. The feedback loop continuously refines the association rules based on observed customer behavior, improving both the precision of difficulty quantification and the reliability of outcome predictions over time.
Solution Approach 2:
The patent transforms traditional analysis by introducing confidence values as a new parameter that directly measures the likelihood of customer achieving goals. This parameter change from simple metric collection to probabilistic prediction enhances both the precision of difficulty quantification and the reliability of outcome predictions by providing a statistically grounded measure of customer success probability.
Data Source
AI summary
An approach is provided that receives, over a computer network, transaction data from a number of clients that are running an app. The approach generates association rules by inputting the transaction data to an association rule learning algorithm, such as an Apriori algorithm. Each association rule is based on a user transaction pattern and a desired result, and each association rule includes a generated confidence value that pertains to an expected performance of one of the steps included in the respective association rule. The app is then modified based on an analysis of the generated confidence values, with the app modification being directed towards improving one or more of the confidence values.