Brand Affinity Identification Using Segmented Binary Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to efficiently identify and target users with brand affinities on online platforms, leading to ineffective personalized marketing and product recommendations.
Innovation Solution
The system employs a method that determines brand affinities by analyzing user purchase histories, browsing behaviors, and other activities using logistic regression models and neural networks, allowing for personalized recommendations and promotions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to identify user brand affinities, then the system is simpler to implement, but the accuracy and personalization of marketing recommendations deteriorate
Solution Approach 1:
The patent segments the brand affinity identification process into multiple specialized models: a first binary classification model for determining affinity to specific product brands, a second binary classification model for determining affinity to product brand categories, and a neural network model for identifying similar brands. This segmentation allows each model to specialize in a specific aspect of brand affinity analysis, improving overall measurement precision while managing system complexity through modular design
Solution Approach 2:
The patent applies partial action by selectively using different models for different types of brand affinity queries. The system determines affinity to a particular brand using the first binary classification model, affinity to a brand category using the second binary classification model, and affinity to similar brands using the neural network model. This partial application of specialized models improves accuracy for each specific task without requiring all models to be deployed for every query
2Adaptability or versatility
If comprehensive user data analysis is performed using multiple models, then the personalization of marketing recommendations is improved, but the computational time and resources increase
Solution Approach 1:
The patent implements preliminary action by pre-training the binary classification models and neural network model offline using historical purchase histories and browsing behaviors. The models are trained in advance on comprehensive user data to learn brand affinity patterns, so that during online operation, the system can quickly apply the pre-trained models to new user queries without performing time-consuming training computations in real-time
Solution Approach 2:
The patent segments the computational workload into offline training phase and online inference phase. During offline training, comprehensive user data is analyzed using multiple models to build accurate brand affinity predictions. During online operation, only the lightweight inference step is performed, which significantly reduces computational time while maintaining high personalization capability through the pre-trained models
Data Source
AI summary
A method including a user who has brand affinities about a product brand or a product brand category. The method can include analyzing whether the user has brand affinities for the product brand or the brand category with two binary classification models that can include (a) a model one to determine an affinity to a particular product brand and (b) a model two to determine an affinity to a particular product brand category. The method also can include analyzing whether the user has affinities for a similar product brand or a similar product brand category by a model three neural network. The method can include displaying recommendations and the promotions for a product brand, a product brand category, a similar product brand, or a similar product brand category to the user. Other embodiments are disclosed.