case study of supervised and unsupervised machine learning

Supervised and Unsupervised Machine learning concepts with a case study

1. Supervised & unsupervised Machine Learning Presented by Mrs . M. NIRMALA Assistant Professor/MCA/HICET HINDUSTHAN COLLEGE OF ENGINEERING AND TECHNOLOGY Educate Ethics Excel

2. Supervised Learning The target variable value is predicted by the predictor variables. The model is trained using the independent variables in the supervision of the target variable .   Suppose we want to estimate the count of bikes that will be rented in a city every day: Predicion of bike count that will be rented in a city every day based on the features like season, holiday, weather, humidity, windspeed etc

3. Supervised Learning Predicting the gender of a person based on height and weight

4. Supervised Learning Predicting the class of the plant based on sepallength , sepalwidth , petallength and petalwidth

5. Un Supervised Learning Only Independent Variables and No Target Variables When there is no target variable or dependent variable we try to divide the entire data into a set of groups in these cases. These groups are known as clusters and the process of making these clusters is known as  clustering.

6. Clustering Clustering is a method of grouping the objects into clusters such that objects with most similarities remains into a group and has less or no similarities with the objects of another group. Examples of Clustering   Segmenting the customers Clustering similar documents together Recommending Similar Movies Recommending similar movies

7. Supervised and UnSupervised Learning Properties Definition Unsupervised Types of ML without human Intervention Supervised Happens under Human Supervision Input Data Unlabelled Labelled

8. Supervised and UnSupervised Learning Properties Use of Data Unsupervised A model is given only input variables and no output is given Supervised A model is given Input data (X) and Output Data(Y) and an algorithm to learn the function from input to output When to Use You don’t know what you are looking for in data You know what you are looking for in data Applicable in Clustering and Association Problems Classification and Regression Problems

9. Supervised and UnSupervised Learning Properties Accuracy of the Results Unsupervised May provide less accurate results Supervised Provides more accurate results Algorithms KMeans K Nearest Neighbour Anomaly Detection Hierarchial Clustering Gaussian Mixture Models Frequent Pattern Growth Principal Component Analysis Logistic Regression Linear regression Decision Tree Support Vector Machine Random Forest Naïve Bayes Use cases Recommender System Anomaly Detection Customer Segmentation Spam Filters Price Prediction Weather Forecasting Image recognition

10. Thanks for Watching!