Automated Data Capture and Prediction
The Air Force required a method to modernize and ease airframe maintenance data collection to improve usability, timeliness, and accuracy of data records.
As part of a Phase I SBIR, Illumination Works’ data scientists extracted free text from Air Force maintenance transactions and mission debrief data to perform classification, training, and evaluation to statistically infer drivers and predict likelihood of occurrence of specific maintenance actions based on correlations and ambiguities between free text and categorical variables to improve the accuracy of the data.
- Simplified Mx action documentation required by Airmen
- Improved timeliness and quality of the Mx record to support better supply buy decisions, Mx skills availability, and preventative Mx decisions
- Improved overall accuracy of enumerated codes
- Applied advanced text analytics to look at correlations between free text and categorical variables
- Maintenance Narrative, Work Unit Code, HOW MAL Code, Action Taken Code, and other maintenance details
- Natural language processing, machine learning, modern workforce tools
- Predictive analytics, machine/adaptive learning, algorithm development, text analytics, entity extraction and classification, data modeling and federation, automated data pipeline