Regression Model for E-commerce Decision Factor Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
E-commerce sellers face difficulties in determining the factors contributing to best-selling products and designing effective webpages, as existing statistical data from E-commerce websites does not easily reveal key product features or webpage specifications that attract buyers, hindering their ability to enhance sales performance.
Innovation Solution
A decision factors analyzing device and method that connects with E-commerce servers to extract consumer history data, recognize product sequences, obtain feature groups, select key decision factors, and train regression models to identify the most influential features for product purchases, thereby providing insights for product design and marketing strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sellers rely on statistical information and historic records from E-commerce websites to determine best-selling products, then they can identify which products are best-selling, but they cannot easily determine the factors that cause these products to be well sold
Solution Approach 1:
The patent introduces an intermediary system comprising a data extraction module, decision factors management module, and regression model management module that mediates between the raw statistical data from E-commerce websites and the sellers' need for decision factor analysis. This intermediary system automatically extracts consumer history data, recognizes product sequences, and trains regression models to identify key decision factors, thereby resolving the information loss without requiring sellers to directly handle complex data analysis themselves
Solution Approach 2:
The system enables self-service by automatically performing data extraction, feature recognition, and regression model training without requiring manual intervention from sellers. The decision factors management module autonomously manages the entire analysis process, from reading consumer history data to generating decision factor sequences, allowing sellers to obtain insights passively while the system serves itself
2Productivity
If sellers try to analyze consumer behavior data to identify key product features and webpage specifications, then they can improve purchase rates, but the analysis process becomes extremely complex and difficult to implement
Solution Approach 1:
The patent segments the complex analysis process into distinct functional modules: a data extraction module that reads consumer history data and product information, a decision factors management module that recognizes product sequences and extracts features, and a regression model management module that trains models and generates decision factors. This segmentation transforms the overwhelming complex task into manageable, specialized components that can be implemented and maintained separately
Solution Approach 2:
The patent replaces manual mechanical analysis processes with automated computational systems. Instead of sellers manually analyzing consumer behavior data, the system uses regression models and algorithmic processing to automatically identify decision factors, substituting human analytical effort with automated mechanical-computational processes that are more efficient and scalable
Data Source
AI summary
A decision factors analyzing device and a decision factors analyzing device for analyzing a plurality of decision factors which cause a product of a product type to be purchased are provided. The method includes identifying a plurality of product sequences corresponding to the product type from a plurality of browse history data and a plurality of purchase history data corresponding to a plurality of consumers of a consumer database, wherein each of the product sequences includes a unpurchased product and a purchased product; obtaining a feature sequence according to the produce sequences and a plurality of product information; training a regression model corresponding to the product type according to K decision factors of the feature sequence to obtain an optimized regression model, and obtaining K decision values respectively corresponding to the K decision factors according to the optimized regression model to generate a decision factor sequence corresponding to the product type.