A Production-Ready Machine Learning System for Inclusive Employment: Requirements Engineering and Implementation of AI-Driven Disability Job Matching Platform

2025-08-14

AI Summary

In Italy, only 3.5% of persons with disabilities are employed, and the existing mandatory quota system relies on manual job-candidate matching—each taking 30–60 minutes—resulting in severe scalability and efficiency limitations. Method: We propose and empirically validate a production-ready, AI-driven employment matching system grounded in a participatory requirements engineering framework that jointly optimizes social responsibility constraints and technical performance. The system employs a seven-model ensemble architecture integrating semantic compatibility, geographic accessibility, and employability readiness; leverages LightGBM enhanced by Optuna hyperparameter optimization; and implements a multidimensional weighted scoring algorithm. Contribution/Results: It achieves millisecond-scale inference (<100 ms), high accuracy (F1 = 90.1%), and processes 500,000 candidate–job pairs in under 10 minutes. Deployment increases public employment service capacity by 60–100%, while ensuring fairness, model interpretability, and human-in-the-loop oversight.

Technology Category

• Humans and AI: AI for Accessibility
• Search and Optimization: Algorithm Configuration
• Philosophy and Ethics of AI: AI & Jobs/Labor

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Employment inclusion of people with disabilities remains critically low in Italy, with only 3.5% employed nationally despite mandatory hiring quotas. Traditional manual matching processes require 30-60 minutes per candidate, creating bottlenecks that limit service capacity. Our goal is to develop and validate a production-ready machine learning system for disability employment matching that integrates social responsibility requirements while maintaining human oversight in decision-making. We employed participatory requirements engineering with Centro per l'Impiego di Villafranca di Verona professionals. The system implements a seven-model ensemble with parallel hyperparameter optimization using Optuna. Multi-dimensional scoring combines semantic compatibility, geographic distance, and employment readiness assessment. The system achieves 90.1% F1-score and sub-100ms response times while processing 500,000 candidate-company combinations in under 10 minutes. Expert validation confirms 60-100% capacity increases for employment centers. The LightGBM ensemble shows optimal performance with 94.6-second training time. Thus, advanced AI systems can successfully integrate social responsibility requirements without compromising technical performance. The participatory design methodology provides a replicable framework for developing ethical AI applications in sensitive social domains. The complete system, including source code, documentation, and deployment guides, is openly available to facilitate replication and adaptation by other regions and countries facing similar challenges.

Problem

• Automating job matching for disabled individuals in Italy
• Reducing lengthy manual candidate-company matching processes
• Integrating social responsibility with technical performance requirements

Innovation

• Seven-model ensemble with Optuna hyperparameter optimization
• Multi-dimensional scoring combining semantic compatibility and geography
• LightGBM ensemble achieving 94.6-second training time