AI and Text-Mining Applications for Analyzing Contractor’s Risk in Invitation to Bid (ITB) and Contracts for Engineering Procurement and Construction (EPC) Projects

Abstract

Contractors responsible for the whole execution of engineering, procurement, and construction (EPC) projects are exposed to multiple risks due to various unbalanced contracting methods such as lump-sum turn-key and low-bid selection. Although systematic risk management approaches are required to prevent unexpected damage to the EPC contractors in practice, there were no comprehensive digital toolboxes for identifying and managing risk provisions for ITB and contract documents. This study describes two core modules, Critical Risk Check (CRC) and Term Frequency Analysis (TFA), developed as a digital EPC contract risk analysis tool for contractors, using artificial intelligence and text-mining techniques. The CRC module automatically extracts risk-involved clauses in the EPC ITB and contracts by the phrase-matcher technique. A machine learning model was built in the TFA module for contractual risk extraction by using the named-entity recognition (NER) method. The risk-involved clauses collected for model development were converted into a database in JavaScript Object Notation (JSON) format, and the final results were saved in pickle format through the digital modules. In addition, optimization and reliability validation of these modules were performed through Proof of Concept (PoC) as a case study, and the modules were further developed to a cloud-service platform for application. The pilot test results showed that risk clause extraction accuracy rates with the CRC module and the TFA module were about 92% and 88%, respectively, whereas the risk clause extraction accuracy rates manually by the engineers were about 70% and 86%, respectively. The time required for ITB analysis was significantly shorter with the digital modules than by the engineers.

The Engineering Machine-Learning Automation Platform (EMAP): A Big-Data-Driven AI Tool for Contractors’ Sustainable Management Solutions for Plant Projects

“…This study shows LD as an example when developing the rules for all of the submodules under the ITB Analysis module. Choi et al [41] explained CRC rule for 'Liquidated Damages (LD)' and the related keywords from the contract risk list for a CRC module. These rules were developed by analyzing the ITBs previously collected.…”

“…If a user wants to find a Level 1 risk clause called 'Liquidated Damages', the LD-related sentences are extracted when a sentence containing one of the keywords listed in Level 2. If the relevant risk clause does not exist, 'No detected message' is printed and displayed on the module interface [41]. The CRC module was implemented to EMAP using Python.…”

“…There were about 20 entities used as NER training data, and at least 50 or more used sentences for each entity. Choi et al [41] introduced the detailed module description and development procedures of the TF modules in this section. This study implemented the TF algorithm applied NER using the Python programming language.…”

“…This paper introduces the entire system architecture and development process of EMAP, and it is valuable as an integrated paper introducing all five developed modules (M1-M5). Three other papers introducing the details of each module are being prepared, and among them, one paper on the submodules of the ITB Analysis module (M1) was published [41], and two others are under review or in preparation. As Choi et al [41] described the details of M1, in this paper, the concept and model of M1 are briefly explained.…”

“…Three other papers introducing the details of each module are being prepared, and among them, one paper on the submodules of the ITB Analysis module (M1) was published [41], and two others are under review or in preparation. As Choi et al [41] described the details of M1, in this paper, the concept and model of M1 are briefly explained.…”