Multivariate Skill Demand Forecasting via NLP Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current forecasting techniques are not accurate enough to predict individualized skill demands, making it challenging for employees and organizations to adapt to rapidly changing job requirements due to emerging technologies and market forces, leading to skill gaps.
Innovation Solution
A computer-implemented method using processor units to determine skill shares from job advertisements, create time series of skill demand, extract embeddings using natural language processing, cluster skills, and train a multivariate time series prediction model to forecast future skill demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current forecasting techniques are used, then the forecasting process is simple, but the accuracy of predicting individualized skill demands is insufficient
Solution Approach 1:
The patent segments skill demands into individualized skill levels and categories, analyzing each skill separately rather than as a general trend. This segmentation enables precise measurement of specific skill demands while managing complexity through structured categorization of skills and job roles.
Solution Approach 2:
The patent transforms job advertisement text into quantitative parameters including skill mentions, skill levels, and frequency counts. By converting unstructured text into structured numerical data, the system achieves high prediction accuracy while maintaining manageable system complexity through standardized parameter extraction.
2Adaptability or versatility
If skill set changes are made rapidly due to emerging technologies, then adaptability to new technologies improves, but skill gaps increase as employees cannot keep up
Solution Approach 1:
The patent performs preliminary analysis of job advertisements to identify emerging skill demands before they become widespread requirements. By detecting skill trends in advance through text mining and pattern recognition, the system enables employees and organizations to prepare skill development plans proactively, maintaining both adaptability and skill adequacy.
Solution Approach 2:
The patent establishes a feedback mechanism that continuously monitors job advertisement data and compares current skill levels with emerging requirements. This feedback loop enables real-time detection of skill gaps and triggers targeted skill development interventions, ensuring employees maintain adequate skills while adapting to technological changes.
3Ease of operation
If employees perform research and analysis to determine future skill demands, then skill acquisition decisions improve, but time and resources are consumed
Solution Approach 1:
The patent implements a self-service system that automatically extracts skill demand information from job advertisements and presents processed insights to employees. By automating the research and analysis process through AI-powered text mining and skill trend detection, the system eliminates manual research efforts while providing actionable skill development recommendations.
Solution Approach 2:
The patent replaces manual research and analysis mechanisms with automated computational systems. Machine learning algorithms process job advertisement text and generate skill demand forecasts, substituting human analytical efforts with efficient computational processes that consume minimal time and resources.
Data Source
AI summary
A computer implemented method determines skill shares for skills from job advertisements. A skill share for a skill identifies a number of times a skill has appeared in job advertisements during a given period of time. The computer implemented method creates a time series of skill demand using the skill shares. The computer implemented method extracts embeddings from job advertisements for an occupation using natural language processing. The computer implemented method clusters the skills using the embeddings to form skill clusters. The computer implemented method defines a training dataset using as a time series of skill demand for all skills within a cluster containing a selected skill to be predicted. The computer implemented method trains a time series prediction model using the training dataset.