Scribd
Upload
18 views2 pages

Data Analytics Unit4 Object Segmentation Notes

The document covers key concepts in data analytics, focusing on object segmentation, regression vs segmentation, and supervised vs unsupervised learning. It outlines the process of tree building for decision trees and introduces multiple decision-making methods for evaluating options based on criteria. Examples and applications are provided for each concept, emphasizing their relevance in real-world scenarios.

Uploaded by

ashoklakavath48
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views2 pages

Data Analytics Unit4 Object Segmentation Notes

The document covers key concepts in data analytics, focusing on object segmentation, regression vs segmentation, and supervised vs unsupervised learning. It outlines the process of tree building for decision trees and introduces multiple decision-making methods for evaluating options based on criteria. Examples and applications are provided for each concept, emphasizing their relevance in real-world scenarios.

Uploaded by

ashoklakavath48
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Data Analytics – Unit 4: Object Segmentation

(Exam Notes)

1■■ Regression vs Segmentation


Regression:
- Regression predicts a continuous numeric value based on input data.
- Example: Predicting sales, temperature, or house price.

Segmentation:
- Segmentation divides a dataset into meaningful groups based on similarities.
- Example: Dividing customers by age, income, or behavior.

Difference:
Basis Regression Segmentation
Output Type Continuous value Group or class
Purpose Prediction Classification / Clustering
Example Predicting price Dividing customers
Learning Type Supervised Supervised / Unsupervised

2■■ Supervised Learning


Supervised learning uses labeled data (inputs and known outputs).
The algorithm learns patterns from this data to make predictions.

Examples: Decision Tree, Linear Regression, Random Forest, SVM


Applications: Email spam detection, Credit score prediction, Disease diagnosis.

3■■ Unsupervised Learning


Unsupervised learning deals with unlabeled data (only inputs).
The algorithm finds patterns, clusters, or relationships automatically.

Examples: K-Means Clustering, Hierarchical Clustering, PCA


Applications: Customer segmentation, Market basket analysis, Anomaly detection.

4■■ Tree Building


Tree Building constructs a Decision Tree for classification or regression.

Steps:
1. Select Root Node (best feature using Gini Index or Information Gain).
2. Split Data into smaller groups.
3. Continue splitting until leaf nodes are pure.
4. Pruning removes unnecessary branches.

Types:
- Classification Tree → Predicts categories
- Regression Tree → Predicts numeric values

Key Terms: Overfitting, Pruning, Complexity


Applications: Loan approval, Medical diagnosis, Marketing decisions.

5■■ Multiple Decision Making


Multiple Decision Making (MDM) helps choose the best option among several based on multiple
criteria.

Steps:
1. Identify problem and alternatives.
2. Set evaluation criteria (cost, quality, risk).
3. Assign weights to each criterion.
4. Evaluate all options.
5. Choose the best decision.

Methods: Decision Tree Analysis, Weighted Scoring, Analytic Hierarchy Process (AHP)
Applications: Business strategy, Project selection, Resource allocation.

You might also like