Account Sharing Profiling Using Usage and Location Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for preventing account sharing in Over-The-Top (OTT) video services are inadequate, as they often fail to accurately detect unauthorized access and can annoy customers, leading to lost revenue and compromised security.
Innovation Solution
A method and apparatus that profile account credential sharing by analyzing consumption data, location information, and IP addresses to identify groups of devices using a single account, applying a learning model to determine sharing severity and nature, and selecting appropriate mitigation strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If providers limit the number of devices per account or concurrent viewing streams, then account sharing is reduced, but false positives increase and customer experience deteriorates
Solution Approach 1:
The system changes multiple parameters simultaneously including device characteristics, location data, usage patterns, and timing information to create a multi-dimensional profile. This allows accurate detection of sharing behavior without relying on simple thresholds that cause false positives, thereby maintaining customer experience while improving detection reliability.
Solution Approach 2:
The system implements feedback loops where detected sharing patterns are continuously analyzed and used to refine detection algorithms. This allows the system to learn from false positives and adjust its behavior, improving accuracy over time while maintaining good customer experience through adaptive mitigation strategies.
2Reliability
If providers implement device logout or password reset measures, then unauthorized access is blocked, but legitimate customers are annoyed and revenue is lost
Solution Approach 1:
The system dynamically adjusts mitigation strategies based on the confidence level of sharing detection. Instead of always applying harsh measures like password resets, the system can apply graduated responses ranging from gentle warnings to targeted interventions, preserving revenue by maintaining access for legitimate customers while still protecting against unauthorized sharing.
Solution Approach 2:
The system applies different mitigation strategies to different accounts based on their specific sharing patterns and risk profiles. Rather than a one-size-fits-all approach, legitimate customers experience no disruption while those with high-confidence sharing violations receive targeted interventions, thus protecting revenue while maintaining security.
3Device complexity
If providers use simple device counting methods, then implementation is easy, but detection accuracy is insufficient
Solution Approach 1:
The system uses a unified multi-factor analysis framework that processes various types of data (device info, location, usage patterns, timing) through a single coherent model. This universal approach provides high detection accuracy without requiring multiple separate simple systems, achieving precision while maintaining reasonable implementation complexity.
Data Source
AI summary
Aspects of the subject disclosure may include, for example, a system or method that determines, based on consumption data and location information, groups of access portals, where the consumption data and the location information correspond to a time period in which the access portals are used to access a service using an account. The groups can be adjusted according to an intended benefit unit for the service and a sharing structure can be determined including benefit unit partitions for the account based on the adjusting. Factors can be determined, based on the benefit unit partitions, that are indicative of account sharing, as well as weights for the factors by applying a learning model to the consumption data. An intervention strategy can be selected from a group of intervention strategies according to the factors and the weights for the factors. Other embodiments are disclosed.