Knowledge Discovery in Databases
- [University of New South Wales, Australia]
- Overview
Knowledge discovery in databases (KDD) is the process of finding patterns in data that are useful, novel, and understandable. KDD is also known as data mining.
KDD is a general process that involves:
- Finding patterns in a dataset
- Mapping low-level data into other forms
- Finding, transforming, and refining meaningful patterns and data
- Representing discovered knowledge in a meaningful and actionable form
The first step in the KDD process is data selection, which involves gathering data from various sources to form a raw dataset. The final step is knowledge representation, which involves creating visualizations using various graphical representation methods.
KDD can have many advantages, including:
- Improving decision-making
- Increasing efficiency
- Better customer service
- Fraud detection
- Predictive modeling
However, KDD can also have some disadvantages, including: privacy concerns, complexity, unintended consequences, data quality, high cost, overfitting.
[More to come ...]
