Thomas A. Grossman

Thomas A. Grossman, Yuan Chen, Sopiko Datuashvili

This paper investigates how GPT-based tools can assist in building reusable analytical spreadsheet models. After a screening, we evaluate five GPT extensions and select Excel AI by pulsrai.com for detailed testing. Through structured experiments on simple problem statements, we assess Excel AI's performance against the ERFR criteria (each input in a cell; cell formulas; no hardwired numbers; labels; accurate). Results show that while Excel AI can produce well-structured models, it is inconsistent and often non-reproducible. We identify two central challenges - "the problem of confidence" and "the problem of workflow" - which highlight the need for skilled users to verify and adapt GPT-generated spreadsheets. Though GPTs show promise for generating draft models that may reduce development time or lower skill requirements, current tools remain unreliable for professional use. We conclude with recommendations for future research into prompt engineering, reproducibility, and larger-scale modeling tasks.

Thomas A. Grossman, Vijay Mehrotra, Mouwafac Sidaoui

We present a widely-used operations management model used in supply and distribution planning, that is typically embedded in a periodic business process that necessitates model modification and reuse. We consider three alternative spreadsheet implementations, a data-driven design, a canonical (textbook) design, and a novel (table-driven) technical design. We evaluate each regarding suitability for accuracy, modification, analysis, and transfer. We consider the degree of training and technical sophistication required to utilize each design. The data-driven design provides insight into poor spreadsheet practices by naïve modelers. The technical design can be modified for new data and new structural elements without manual writing or editing of cell formulas, thus speeding modification and reducing risk of error. The technical design has potential for use with other classes of models. We identify opportunities for future research.