Industry Classifier Using Dual ML Algorithms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge lies in accurately predicting and updating the industries practiced by companies on social networking platforms, as these classifications often remain static and fail to reflect changes or new industries, leading to irrelevant search results due to the lack of manual updates by companies or third parties.
Innovation Solution
Implementing multiple computer-implemented classifiers within a machine learning system that periodically update industry classifications without human intervention, using existing and new industry classifiers trained on different machine learning algorithms to predict industries based on evolving taxonomy and third-party information sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual updates are used to keep industry classifications current, then accuracy of industry classification is improved, but labor cost and time consumption increase
Solution Approach 1:
The system performs automatic industry classification updates using machine learning classifiers that analyze company data and taxonomy changes without human intervention. The classifiers continuously self-update industry assignments as companies evolve or as taxonomy structures change, eliminating the need for manual classification maintenance while preserving high accuracy through algorithmic analysis of relevant features.
Solution Approach 2:
The machine learning classifiers are pre-trained on historical industry classification data and taxonomy structures before deployment. This preliminary training enables the system to automatically adapt to taxonomy changes and company evolution patterns, allowing it to maintain accurate classifications proactively rather than requiring reactive manual updates after changes occur.
2Adaptability or versatility
If multiple machine learning classifiers are deployed to track company and taxonomy changes, then adaptability of industry classification is improved, but system complexity increases
Solution Approach 1:
The classification system is divided into multiple specialized machine learning classifiers, each trained on specific subsets of industry taxonomy and company data. This segmentation allows each classifier to focus on particular industry domains or change patterns, improving adaptability to different types of taxonomy evolution while managing overall system complexity through modular, independent classifier components that can be developed and maintained separately.
Data Source
AI summary
In an example embodiment, a solution that automatically predicts an industry for a candidate company is provided. An existing industry classifier is trained using a first machine learning algorithm, the first machine learning algorithm taking as input first training data and existing industries listed in an industry taxonomy. A new industry classifier is trained using a second machine learning algorithm, the second machine learning algorithm taking as input second training data and new industries listed in an industry taxonomy. Then the candidate company is fed into the existing industry classifier, producing one or more predicted existing industries corresponding to the candidate company. The candidate company is also fed into the new industry classifier, producing one or more predicted new industries corresponding to the candidate company. One or more final predicted industries are selected from among the one or more predicted existing industries and the one or more predicted new industries.