{"id":1842,"date":"2026-02-23T09:41:06","date_gmt":"2026-02-23T02:41:06","guid":{"rendered":"https:\/\/base.binus.ac.id\/business-engineering\/?p=1842"},"modified":"2026-02-23T09:41:11","modified_gmt":"2026-02-23T02:41:11","slug":"classification-in-data-mining","status":"publish","type":"post","link":"https:\/\/base.binus.ac.id\/business-engineering\/2026\/02\/23\/classification-in-data-mining\/","title":{"rendered":"Classification in Data Mining"},"content":{"rendered":"

Classification in Data Mining<\/h1>\n

Businesses collect enormous amounts of data every day, such as transactions, customer behavior, sensor readings, website activity, etc.<\/p>\n

However, raw data alone doesn't create value. Hence, data mining methods are used to give values to data by answering questions that involve prediction and\/or labeling, one of which is through a method called classification.<\/p>\n

 <\/p>\n

What is Classification?<\/h2>\n

Classification is a data processing technique that filters and groups data according to the similar criteria possessed by each piece of data [1], [2]. Groupings from this method are not random guesses. Instead, this method lets the model learn from past labeled examples to help it predict labels for new data.<\/p>\n

For example:<\/p>\n\n\n\n\n\n\n\n\n
Problem<\/strong><\/td>\nClassification Output<\/strong><\/td>\n<\/tr>\n
Email filtering<\/td>\nSpam \/ Not Spam<\/td>\n<\/tr>\n
Loan approval<\/td>\nApprove \/ Reject<\/td>\n<\/tr>\n
Customer churn<\/td>\nStay \/ Leave<\/td>\n<\/tr>\n
Product quality<\/td>\nDefective \/ Non-Defective<\/td>\n<\/tr>\n
Medical diagnosis<\/td>\n[Disease] \/ Healthy<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Usually, classification outputs are in discrete classes and not numbers. This is what makes classification different from prediction methods like regression.<\/p>\n

 <\/p>\n

How Classification Works<\/h2>\n

A classification model follows three main stages:<\/p>\n

1. Training<\/h3>\n

At this stage, the model studies historical labeled data.<\/p>\n

Example dataset:<\/p>\n\n\n\n\n\n\n
Customer Age<\/strong><\/td>\nMonthly Usage<\/strong><\/td>\nChurn<\/strong><\/td>\n<\/tr>\n
21<\/td>\nLow<\/td>\nYes<\/td>\n<\/tr>\n
45<\/td>\nHigh<\/td>\nNo<\/td>\n<\/tr>\n
30<\/td>\nMedium<\/td>\nNo<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

The algorithm will then learn patterns that connect features to the outcomes.<\/p>\n

2. Learning the Pattern<\/h3>\n

The algorithm builds decision rules based on the learned dataset. Based on the example dataset, it may catch on that customers of young age, with low usage, are more likely to churn. This step is also known as the \"intelligence building\" phase.<\/p>\n

3. Prediction<\/h3>\n

After understanding the algorithm and identifying the patterns, the model will now be given new data to predict outcomes.<\/p>\n

New data example:<\/p>\n\n\n\n\n
Customer Age<\/strong><\/td>\nMonthly Usage<\/strong><\/td>\n<\/tr>\n
24<\/td>\nLow<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

The model will most likely predict that it will churn (churn = yes), because this data shows a customer of young age with low monthly usage. Based on historical data, this type of dataset shows a positive result of churning.<\/p>\n

 <\/p>\n

Common Classification Algorithms<\/h2>\n