Data-driven Value-engineering Frameworks for Enhancing Productivity and Compliance in Federally Funded Highway Projects
Year: 2019
Type: article
Abstract: Traditional Value Engineering (VE) methodologies in federally funded highway projects suffer from subjectivity, reliance on limited expert opinion, and a failure to dynamically integrate predictive data, often resulting in suboptimal outcomes and compliance risks.This research proposes and validates the Data-Driven Value Engineering System (DDVES), a six-layered architectural framework that integrates Artificial Intelligence (AI), Machine Learning (ML), and Explainable AI (XAI) to transform value management into a continuous, objective, and auditable process.The DDVES utilizes a Predictive Analytics Engine to forecast project performance with high accuracy (3.4% Mean Absolute Percentage Error for cost) and employs a Dynamic Multi-Criteria Decision-Making Engine, weighted heavily toward Regulatory Compliance Risk Reduction (0.35 weight).Validation through retrospective case studies revealed that DDVES-generated recommendations offer significant improvements, leading to an average of 8.4% better Schedule Performance Index (SPI) compared to traditional VE outcomes.The system enhances decision-making consistency by 24.3% through the use of XAI-generated rationales, establishing a Harshit Sheladiya, Jigar Variyavwala https://iaeme.com/Home/journal/JCIET18 editor
Authors: Harshit Sheladiya, Jigar Variyavwala
Language: English
Subfield: Strategy and Management
Domain: Social Sciences
Open Access status: bronze
OpenAlex ID: W7124147692