R-DAIR is an open, self-administered revenue-data assurance standard designed for small enterprises, credit unions, community banks, cooperatives, and other institutions that need continuous visibility into record integrity but cannot rely on large data governance teams. The standard combines four maturity dimensions, five capability levels, measurable data-quality indicators, robust anomaly detection, owner-routed alerting, and explicit detection-latency accounting. This white paper extends the original R-DAIR design with a 90-day, eight-site pilot comprising 356 staff, 177,400 customer/master records, and 1,039,810 observed transactions. Across the pilot, record-weighted completeness was 96.15%, duplicate rate 2.32%, staleness 15.19%, validity 98.12%, and consistency 97.23%. Field anomaly detection produced 357 true positives, 48 false positives, and 29 false negatives, corresponding to overall precision of 0.881, recall of 0.925, and F1 of 0.903. The median detection latency was 29 seconds (IQR 16-48 seconds; 95th percentile 94 seconds), while median alert dispatch latency was 8 seconds. Average maturity rose from 2.22 to 3.47 across the four dimensions, with the largest gain in anomaly detection and revenue assurance. Sensitivity analysis showed that the default amount-outlier multiplier k=3.0 delivered the highest F1 among tested settings. The results support R-DAIR as a practical  continuous-assurance architecture while also identifying important validation needs,especially inter-rater reliability, site-level D2 construct validation, usability measurement, and broader external replication.

References

 Adeyekun, A. A. (2024). Artificial intelligence framework for predictive sediment dynamics and environmental vulnerability assessment in data-limited coastal systems. Journal of Computational Analysis and Applications, 33(2), 1133-1158.

 Adeyekun, A. A., Orekoya, O. H., & Abiola, O. A. (2023). Data-driven monitoring and modelling of coastal and sedimentary systems for climate resilience. International Journal of Data Science and Engineering, 1(1), 10-42. https://doi.org/10.34218/IJDSE_01_01_002

 Ashimolowo, M. B. (2024). A computational model for risk-based quality governance assessment in high-risk infrastructure projects: A weighted composite scoring approach. Journal of Computational Analysis and Applications, 33(8), 8352-8374.

 Ashimolowo, M. B., & Oginni, A. G. (2022). Quality governance and performance stability in high risk projects: A framework for strategic assurance. International Journal of Scientific Research and Modern Technology, 1(2), 16-40. https://doi.org/10.38124/ijsrmt.v1i2.1282

 Batini, C., Cappiello, C., Francalanci, C., & Maurino, A. (2009). Methodologies for data quality assessment improvement. ACM Computing Surveys, 41(3), Article 16. https://doi.org/10.1145/1541880.1541883

 Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), Article 15. https://doi.org/10.1145/1541880.1541882

 DAMA International. (2017). DAMA-DMBOK: Data management body of knowledge (2nd ed.). Technics Publications.

 de Bruin, T., Freeze, R., Kulkarni, U., & Rosemann, M. (2005). Understanding the main phases of developing a maturity assessment model. In Proceedings of the 16th Australasian Conference on Information Systems (ACIS 2005) (Paper 109).

 International Organization for Standardization. (2016). ISO 8000-61:2016 Data quality - Part 61: Data quality management: Process reference model. ISO.

 National Institute of Standards and Technology. (2023). Artificial intelligence risk management framework (AI RMF 1.0) (NIST AI 100-1). U.S. Department of Commerce. https://doi.org/10.6028/NIST.AI.100-1

 Olaseinde, A. J. (2024). The speed of theft: Developing real-time detection protocols for authorized push payment (APP) fraud in instant payment systems. Journal of Computational Analysis and Applications, 33(6), 4034-4059.

 Olaseinde, A. J., & Azeez, B. B. (2022). The trust paradox: Analyzing auditor reliance on hallucinating generative AI models in internal control testing. International Journal of Artificial Intelligence Engineering and Transformation, 3(1), 38-49. https://doi.org/10.54660/IJAIET.2022.3.1.38-49

 Pipino, L. L., Lee, Y. W., & Wang, R. Y. (2002). Data quality assessment. Communications of the ACM, 45(4), 211-218. https://doi.org/10.1145/505248.506010

 Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3), e0118432. https://doi.org/10.1371/journal.pone.0118432

 Tukey, J. W. (1977). Exploratory data analysis. Addison-Wesley.

 Wang, R. Y., & Strong, D. M. (1996). Beyond accuracy: What data quality means to data consumers. JournalofManagementInformationSystems,12(4),5-33. https://doi.org/10.1080/07421222.1996.11518099