Data Mining Algorithms: Introduction

These flashcards cover the key concepts and processes discussed in the Data Mining Algorithms lecture notes.

What is the main objective of Data Mining?

To extract interesting (non-trivial, implicit, previously unknown and potentially useful) information or patterns from large databases.

What are the three types of learning methods in Data Mining and Machine Learning?

Descriptive Learning, Predictive Learning, and Prescriptive Learning.

What is the Knowledge Discovery Process (KDD Process)?

The KDD Process involves data cleaning, data integration, data selection, transformation, data mining, pattern evaluation, and knowledge presentation.

List some basic data mining tasks.

Frequent Pattern Mining, Clustering, Classification, Regression, and Process Mining.

What is Frequent Itemset Mining?

A task in data mining that involves identifying frequently co-occurring items in transaction databases.

What is the purpose of the KDD process focusing on Task-Relevant Data?

To find useful features and create a target data set by selecting relevant tuples and attributes from the database.

What is the role of data cleaning in the KDD process?

It involves the elimination of inconsistencies, noise, and computation of missing values in datasets.

What applications does Clustering have in Data Mining?

Customer profiling/segmentation, document or image collections, and web access patterns.

What does the term 'data explosion' refer to?

The tremendous amounts of data caused by automated data collection and mature database technology.

What is one application of Regression in Data Mining?

Building a model to predict housing values based on known numerical data.