Propensity-Based SMS Invitation Filtering for Social Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Social networks face low conversion rates of invitations to actual signups when sending SMS invitations, resulting in high costs due to sending invitations to uninterested contacts.
Innovation Solution
A propensity-based SMS invitation filtering system that determines and prioritizes sending invitations to individuals with higher propensities to accept by analyzing features associated with the inviter, invitee, and invitation, using a propensity model to rank and filter contacts, and optimizing the timing and format of invitations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If SMS invitations are sent to all contacts in address books, then the quantity of invitations sent increases, but the conversion rate to actual signups decreases and cost per acquisition increases
Solution Approach 1:
The patent applies local quality by segmenting the contact population into different groups based on their invitation propensity scores. Instead of treating all contacts uniformly, the system identifies and targets specific high-propensity segments with personalized SMS invitations, while excluding low-propensity contacts. This selective approach improves conversion rates by focusing resources on the most responsive segments.
Solution Approach 2:
The system changes the parameter of invitation targeting from broad coverage to precision targeting by calculating propensity scores for each contact. By transforming the invitation strategy from quantity-based to quality-based selection using predictive modeling, the system achieves higher conversion rates with fewer invitations sent.
2Quantity of substance
If SMS invitations are sent to all contacts, then the coverage of potential users increases, but the cost per acquisition becomes prohibitively high
Solution Approach 1:
The patent applies partial action by sending SMS invitations only to a subset of contacts who score above a certain propensity threshold, rather than sending to all contacts. This partial targeting approach maintains adequate user acquisition while significantly reducing the cost per acquisition by avoiding waste on unresponsive contacts.
Solution Approach 2:
The system uses historical data and machine learning models to automatically identify high-propensity contacts without manual intervention. The propensity model self-services the invitation list generation by ranking contacts based on their likelihood to convert, eliminating the need for manual contact selection and enabling cost-effective scaling.
3Ease of operation
If invitations are sent without filtering, then the simplicity of the invitation process is maintained, but the efficiency of invitation delivery decreases
Solution Approach 1:
The patent introduces a propensity scoring system as an intermediary layer between the invitation request and the actual SMS delivery. This intermediary automatically filters and ranks contacts based on their likelihood to convert, maintaining operational simplicity for users while dramatically improving invitation delivery efficiency through data-driven selection.
Data Source
AI summary
The disclosed embodiments provide a system for propensity-based SMS (Short Message Service) invitation filtering. During operation, the system collects multiple contact numbers associated with multiple invitation requests into a total set of contact numbers. Then, for one or more of the contact numbers, the system determines a propensity for a person associated with the contact number to click on a link in an electronic invitation sent to the contact number and subsequently create an account. Clicking on the link may connect the person to a user community that he or she has been invited to join. Once the propensity has been determined, the system ranks the contact numbers in the total set of contact numbers according to the propensities. Finally, for each contact number in the total set of contact numbers that is ranked above a specified threshold, the system processes an invitation for the contact number.