SuretyAssist: Fuzzy Expert System to Assist Surety Underwriters in Evaluating Construction Contractors for Bonding
Bibliographic record
Abstract
In construction, many owners mitigate the risk of unforeseen contractor default by accepting only bonded contractors who must endure a rigorous evaluation process by surety brokers and surety underwriters. This evaluation process includes a financial analysis and a review of work on hand and past performance, all of which have reliable structured methods for their evaluation. Additionally, a number of subjective criteria are considered that are more difficult to capture and assess objectively but which can be modeled effectively using fuzzy logic. The purpose of this paper is to illustrate how fuzzy logic and expert systems can be combined to provide a structured approach to evaluating contractors for surety underwriting purposes. Fuzzy logic is used to model both the objective and subjective factors considered in contractor evaluation using linguistic terms, and expert rules are used to capture the surety experts’ reasoning process. A fuzzy expert system, SuretyAssist, is presented that can be used to provide an initial evaluation of general contractors as well as periodic reviews to determine whether or not to accept them as clients for bonding. SuretyAssist was validated using 31 actual cases of contractor evaluation and found to be accurate in 81% of the cases.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".