Fake E-Shop Detection Using HTML Indicators and ML Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to reliably detect fake e-shops, which deceive consumers with fraudulent online stores that mimic legitimate brands, leading to financial loss, identity theft, and brand damage.
Innovation Solution
A system and method using a processor and machine learning model to analyze website indicators, including HTML content and external data, to identify and block access to fake e-shops by applying feature engineering and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models and feature engineering are applied to analyze website indicators, then detection accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the detection process into distinct modules: HTML content extraction, indicator extraction, feature engineering, and machine learning classification. Each module handles a specific aspect of the analysis, making the complex system more manageable and maintainable while improving detection accuracy through specialized processing at each stage.
Solution Approach 2:
Feature engineering acts as an intermediary between the raw website indicators and the machine learning model. It transforms and preprocesses the extracted indicators into a format suitable for classification, bridging the gap between data extraction and intelligent decision-making, thereby improving detection accuracy without directly increasing model complexity.
2Reliability
If comprehensive website indicators are extracted and analyzed, then detection reliability is improved, but processing time increases
Solution Approach 1:
The system performs preliminary extraction and categorization of website indicators during the feature engineering stage. By pre-processing and organizing the indicators into meaningful features before final classification, the system reduces processing time during the actual detection while maintaining comprehensive analysis for reliable results.
Solution Approach 2:
Different weights and processing depths are applied to different types of website indicators based on their importance and reliability. Critical indicators receive more thorough analysis while less significant ones are processed more lightly, optimizing the balance between detection reliability and processing time.
Data Source
AI summary
A method, apparatus, and system for website filtering includes a processor and a memory having stored therein at least programs or instructions executable by the processor to cause the system to load HTML content of a requested website, extract website indicators from the loaded HTML content, perform feature engineering on the extracted website indicators, filter the website by applying a machine learning model trained to analyze the engineered website indicators to predict whether a resource of the website is associated with a fake e-shop, and if it is determined that a resource of the requested website is associated with a fake e-shop, generate and transmit a website filter determination that the resource of the website is associated with a fake e-shop.