This document discusses supervised and unsupervised machine learning techniques. Supervised learning uses labeled training data to learn classifications and regressions, while unsupervised learning finds hidden patterns in unlabeled data through techniques like clustering. It provides k-means clustering as an example of unsupervised learning, where the algorithm divides data into a predefined number of clusters based on similarity. The document proposes using k-means clustering on customer data from a supermarket mall to segment customers into groups to help with marketing strategy.

2. INTRODUCTION
MACHINE LEARNING TECHNIQUES ARE BROADLY DIVIDED INTO TWO PARTS :
• SUPERVISED MACHINE LEARNING
• UNSUPERVISED MACHINE LEARNING

3. SUPERVISED MACHINE LEARNING
• IN SUPERVISED MACHINE LEARNING, THE DATA IS LABELLED AND THE ALGORITHM LEARNS FROM
LABELLED TRAINING DATA. EXAMPLES OF THIS METHOD ARE CLASSIFICATION AND REGRESSION.

4. UNSUPERVISED MACHINE LEARNING
• IN UNSUPERVISED MACHINE LEARNING, WE DO NOT NEED TO SUPERVISE THE MODEL. SUCH A METHOD
DEALS WITH UNLABELED DATA. UNSUPERVISED MACHINE LEARNING HELPS US FIND HIDDEN AND
UNKNOWN PATTERNS IN DATA.

5. • OFTEN IT EASIER TO GET UNLABELLED DATA AS COMPARED TO LABELLED DATA, AND IN SUCH CASES, WE
CAN USE UNSUPERVISED MACHINE LEARNING TO WORK ON THE DATA. DATA,WHICH NEEDS
CATEGORIZATION CAN BE CATEGORIZED WITH THE HELP OF UNSUPERVISEDMACHINE LEARNING.

6. CLUSTERING
• CLUSTERING IS A TYPE OF UNSUPERVISED MACHINE LEARNING IN WHICH THE ALGORITHM PROCESSES
OUR DATA AND DIVIDED THEM INTO “CLUSTERS”.
• CLUSTERING ALGORITHMS TRY TO FIND NATURAL CLUSTERS IN DATA, THEVARIOUS ASPECTS OF HOW
THE ALGORITHMS TO CLUSTER DATA CAN BE TUNED AND MODIFIED. CLUSTERING IS BASED ON THE
PRINCIPLE THAT ITEMS WITHIN THE SAME CLUSTER MUST BE SIMILAR TOEACH OTHER. THE DATA IS
GROUPED IN SUCH A WAY THAT RELATED ELEMENTS ARE CLOSE TO EACH OTHER.

8. USES OF CLUSTERING
• MARKETING
• REAL ESTATE
• BOOKSTORE AND LIBRARY MANAGEMENT
• DOCUMENT ANALYSIS

9. K-MEANS CLUSTERING
• K-MEANS CLUSTERING IS AN UNSUPERVISED MACHINE LEARNING ALGORITHM THAT DIVIDES THE GIVEN
DATA INTO THE GIVEN NUMBER OF CLUSTERS. HERE, THE “K” IS THE GIVEN NUMBER OF PREDEFINED
CLUSTERS, THAT NEED TO BE CREATED.

10. THE CHALLENGE
• YOU ARE OWING A SUPERMARKET MALL AND THROUGH MEMBERSHIP CARDS, YOU HAVE SOME BASIC
DATA ABOUT YOUR CUSTOMERS LIKE CUSTOMER ID, AGE, GENDER, ANNUALINCOME AND SPENDING
SCORE. YOU WANT TO UNDERSTAND THE CUSTOMERS LIKE WHO ARE THE TARGET CUSTOMERS SO THAT
THE SENSE CAN BE GIVEN TO MARKETING TEAM AND PLAN THE STRATEGY ACCORDINGLY.

11. MALL CUSTOMER DATA: IMPLEMENTATION
OF K-MEANS
• MALL CUSTOMER DATA IS AN INTERESTING DATASET THAT HAS HYPOTHETICAL CUSTOMER DATA.
• YOU HAVE CUSTOMER DATA, AND ON THIS BASIS OF THE DATA, YOU HAVE TO DIVIDE THE CUSTOMERS
INTO VARIOUS GROUPS.

12. FEATURES IN DATA SET
• CUSTOMER ID
• CUSTOMER GENDER
• CUSTOMER AGE
• ANNUAL INCOME OF THE CUSTOMER (IN THOUSAND DOLLARS)
• SPENDING SCORE OF THE CUSTOMER (BASED ON CUSTOMERBEHAVIOUR AND SPENDING NATURE)

20. ADVANTAGES
• DETERMINE APPROPRIATE PRODUCT PRICING.
• DEVELOP CUSTOMIZED MARKETING CAMPAIGNS.
• DESIGN AN OPTIMAL DISTRIBUTION STRATEGY.
• CHOOSE SPECIFIC PRODUCT FEATURES FOR DEPLOYMENT.
• PRIORITIZE NEW PRODUCT DEVELOPMENT EFFORTS.
• HTTPS://WWW.KAGGLE.COM/CODE/GCDATKIN/MALL-CUSTOMER-MARKET-SEGMENTATION/DATA