Prevent Low-Quality Analytics by Automatic Selection of the Best-Fitting Training Data.
Cornelia KieferPeter ReimannBernhard MitschangPublished in: HICSS (2020)
Keyphrases
- low quality
- automatic selection
- training data
- high quality
- learning analytics
- test data
- business intelligence
- data sets
- data mining
- classification accuracy
- decision trees
- learning algorithm
- training set
- prior knowledge
- supervised learning
- poor quality
- test set
- least squares
- social media
- training examples
- labeled data
- training process
- big data
- palmprint
- low quality images
- face detection
- training samples
- data management
- denoising
- ground truth
- data analysis