Pandata Tech's Data Quality Method (DQM) for Validating Quality, Useful Data

This research will show how machine learning modeling can help the AF validate data/signals collected from their operations/sensors. Data and signal quality are a big problem in industry when it comes to digitalization, with millions of data points over thousands of signals, unqualified and bad data are everywhere. The method will show the importance of having a validation pipeline, and how it can help other algorithms make better decisions while saving up to 80% of the time data professionals spend cleaning and validating data. Organizations should spend their time optimizing the future not validating data. Our approach uses statistical principles, machine learning and advanced analytics. The method is ISO 8000 compliant and can provide a framework in data management and data quality for the Air Force. Depending on the application, the accuracy of our method will vary. Our proven results are in the 88% - 99% range of accuracy (in offshore drilling). The process has been validated by many organizations with signals ranging from offshore drilling (blow out prevention, dynamic positioning, and tripping), quantitative trading, and supply chain. The research will show possible applications for the USAF and map our conversations with AF personnel who are potential stakeholders.