Personalized Ad Generation Using Abandoned Cart Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for generating online advertisements do not account for abandoned products in users' shopping carts, leading to less relevant ad content and lower sales and site traffic, as they primarily rely on purchase history without considering products that users intended to buy but did not complete the transaction.
Innovation Solution
A method and system that utilize machine learning to generate personalized advertisements by analyzing current user activity data, including product status and financial data, to identify excluded products, rank relevant products, and display them on a graphical user interface, incorporating abandoned products and their categories to create a ranked list for display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If advertisement content is tailored using only purchase history, then the system complexity is reduced, but the relevance of advertisement content deteriorates
Solution Approach 1:
The system performs preliminary actions by capturing and storing abandoned cart information before the purchase is completed. This allows the system to have advance knowledge of user intent and preferences, which is then used to generate more relevant advertisements without significantly increasing system complexity during the ad generation phase.
Solution Approach 2:
The patent introduces an intermediary component (abandoned cart analysis module) that bridges between the e-commerce platform data and the advertisement generation system. This intermediary processes and structures the cart abandonment data, making it usable for ad personalization while isolating the complexity from both the e-commerce platform and the ad serving system.
2Loss of information
If abandoned products are incorporated into advertisement generation, then the relevance of advertisement content is improved, but the device complexity increases
Solution Approach 1:
The system segments the advertisement generation process into distinct modules: one handling traditional purchase history data and another handling abandoned cart data. Each module processes its specific data type independently, and their results are combined to create the final personalized advertisement. This segmentation manages complexity by breaking down the overall system into smaller, more manageable components.
Solution Approach 2:
The patent changes the parameters used in advertisement generation by introducing new variables from abandoned cart data (such as abandoned product IDs, cart timestamp, items in cart) alongside traditional purchase history parameters. This allows the system to leverage additional information for better ad relevance while using established parameter management techniques to control the increased complexity.
3Measurement precision
If machine learning is applied to analyze user activity data, then the precision of product recommendation is improved, but the computational resources required increase
Solution Approach 1:
The system applies machine learning selectively rather than comprehensively - using ML algorithms specifically for analyzing abandoned cart patterns and user behavior, while relying on simpler rule-based or statistical methods for other aspects of ad generation. This partial application of ML achieves improved recommendation precision for the most critical decisions while limiting overall computational resource consumption.
Data Source
AI summary
Systems and methods of generating, for display on a graphical user interface (GUI), a personalized advertisement. The systems and methods can include receiving data indicative of initiating a browsing session, aggregating user activity data associated with a user of the application, the user activity data including current session data and/or past session data, applying machine learning on the user activity data to generate one or more excluded products, applying the one or more excluded products to a product database to generate a list of relevant products, ranking, using one or more ranking rules, the list of relevant products to generate a ranked list of relevant products, and sending, to the mobile device, the personalized advertisement including one or more relevant products from the ranked list of relevant products.