Automated Extraction and Time-Cost Prediction of Contractual Reporting Requirements in Construction Using Natural Language Processing and Simulation

Abstract

Due to a lack of suitable methods, extraction of reporting requirements from lengthy construction contracts is often completed manually. Because of this, the time and costs associated with completing reporting requirements are often informally approximated, resulting in underestimations. Without a clear understanding of requirements, contractors are prevented from implementing improvements to reporting workflows prior to project execution. This study developed an automated reporting requirement identification and time–cost prediction framework to overcome this challenge. Reporting requirements are extracted using Natural Language Processing (NLP) and Machine Learning (ML), and stochastic simulations are used to predict overhead costs and durations associated with report preparation. Functionality and validity of the framework were demonstrated using real contracts, and an accuracy of over 95% was observed. This framework provides a tool to rapidly and efficiently retrieve requirements and quantify the time and costs associated with reporting, in turn providing necessary insights to streamline reporting workflows.

Demystifying the Role of Natural Language Processing (NLP) in Smart City Applications: Background, Motivation, Recent Advances, and Future Research Directions

“…With the help of NLP and some heuristic rules to transform the OO into UML diagrams. • Jafari et al [187] introduced a method to extract relevant information from construction contract documents and predict the time and cost of the project execution before the implementation begins. This approach uses NLP, and ML for the extraction of this information and a stochastic simulation tool for the predictions.…”

Artificial Intelligence in Knowledge Management for Construction-Specific Documents

“…Extraction of reporting requirements from long construction contracts is frequently conducted manually due to a lack of acceptable technologies [44]. As a result, the time and expenses involved with meeting reporting obligations are frequently estimated informally, leading to underestimate.…”

Automation of text document classification in the budgeting phase of the Construction process: a Systematic Literature Review

“…These challenges are aggravated by the austere time constraints in which this task must be performed and the multiple variables that must be considered simultaneously to achieve an accurate prediction (e.g. project duration, resource availability and construction quality or on-site safety, among others) (Jafari et al , 2021). As each project is prepared considering different assumptions with distinct degrees of certainty, these deliverables become susceptible to errors and omissions (Martins, 2009).…”