Generating fully consistent fictional enterprises for business software testing
Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data
Artificial Intelligence
Summary
Creating realistic fake business data usually means copying some real data and making small changes, which can lead to privacy problems. This paper presents a way to build entire imaginary companies from scratch using general information about industries and business models, without relying on any real data. The authors make sure the fake data fits together logically across many business systems and test its realism with new automatic checks. They also provide a service and tools that let users create and simulate these fake businesses for testing software or analysis.
What this means in practice
- •For enterprise software developers: Test business software using fully consistent, realistic fictional company data spanning many integrated systems without risking real data exposure.
- •For business analysts: Create synthetic datasets based on business questions to generate labeled relational databases for analysis training and validation.
Authors
Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary, Omer Niv
Abstract
Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset. This paper describes a generator that has no real dataset at either end. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls, chat messages, and documents, all consistent with one another. One entity graph is projected into the native formats of 66 business products, so the same customer appears in the CRM, the support desk, and the call system under one identity. Because no real counterpart exists, realism is built in from cited reference statistics and verified by reference-free measurement: a five-axis scorecard of 28 statistical checks, an adversarial detector that hunts for the marks of synthetic generation, and a set of soundness checks that include a classifier test against an independently shuffled copy of the data. Because these instruments existed before the generator was tuned, progress is measured under a fixed yardstick: over 23 generated companies, mean realism climbed from 60.3 to 99.1, the weakest company from 41.1 to 94.9, and the detector, which initially flagged 55.2% of all records, now flags none. The scores hold on a seed never used during development. A second generator builds relational databases from a list of business questions. It forces qualifying rows for each answerable question, adds controlled near misses, and computes exact labels from the finished tables. The generator runs as a hosted service at https://console.era.eon.io. A company built there to a specification is served through its simulators over MCP and REST, and the simulators are also published as container images for offline use