Machine Learning and its applications in operations management.pptx

It shows the applications of various machine learning techniques in operations management.

1. Applications of Machine Learning in Management By Dr. Peeyush Vats 1

2. What is Machine Learning 2 Machine Learning allows the systems to make decisions autonomously without any external support. These decisions are made when the machine is able to learn from the data and understand the underlying patterns that are contained within it. T h en, th r oug h p a t t ern m a t ching a n d furthe r anal y si s , t h e y r e turn t he outcome which can be a classification or a prediction.

3. Machine Learning: How it works Machine Learning is similar to human learning. For example, if a child is shown images with specific objects on them, they can learn to identify and differentiate between them. Through data input and certain commands, the computer is enabled to "learn" to identify certain objects (persons, objects, etc.) and to distinguish between them. For instance, the programmer can tell the system that a particular object is a human being (="human") and another object is not a human being (="no human").

4. Advantages Advantages and Disadvantages of Machine Learning 4

5. Types of Machine Learning 5 There are two important types of Machine Learning Algorithms: Supervised Learning Unsupervised Learning

6. Supervised Learning 6 Supervised Learning is the most popular paradigm for performing machine learning operations. It is widely used for data where there is a precise mapping between input-output data. The dataset, in this case, is labeled, meaning that the algorithm identifies the features explicitly and carries out predictions or classification accordingly. As the training period progresses, the algorithm is able to identify the relationships between the two variables such that we can predict a new outcome.

7. Example of Supervised Learning 7

8. Unsupervised Learning 8 Unsupervised Learning No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).

9. Unsupervised Learning 9

10. 10

11. 12

12. Supervised Learning ( Logistics Regression ) 13 Lo g i s tic r e g r e s sio n is a clas s ifi c a tion t ec h niq u e ( s up e r vi s e d learning) produces results in a binary format:

13. Examples of Logistics Regression A student will be “ Admitted or Not Admitted " in a particular institute through GMAT score Investment in particular stock “Risky or Not risky” A patient has a particular diseases “Yes or not” Insurance claim “ Approved or Not Approved " BONUS will be given to the employee " YES or NO " Email Spam Detection “SPAM or NOSPAM”

14. Logistics Regression 15 Steps for Logistics Regression: Understanding about data and problem. Divide the data into two parts called train and test data in the proportion of 80%:20%. Train model on Train data set. Check accuracy of model on Test Data set. 5.Check the validation of model. 6.Explain the variable importance in the model.

15. In this project, we will discuss the use of Logistic Regression to predict the insurance claim. We take a sample of 1338 data which consists of the following features: Age : A ge of the policyholder Sex : G ender of policy holder (female=0, male=1) BMI : Body mass index Children : N umber of children/dependents of the policyholder Smoker : S moking state of policyholder (non-smoke=0;smoker=1) Region : T he residential area of policyholder (northeast=0, northwest=1, southeast=2, southwest=3) Charges : I ndividual medical costs billed by health insurance Insurance claim – The labelled output from the above features, 1 for valid insurance claim / 0 for invalid. 16 Insurance Claim Prediction using Logistic Regression

16. Y=P==gives probability (dependent variable), X1,X2,…,Xn are independent variables . We use MLE to fit this equation. = 𝑃 ( 𝑋1, 𝑋 2 , . . 𝑋 𝑛 ) 𝑒 −0.67667323−.02∗𝑎𝑔𝑒−.164𝑠𝑒𝑥+.08∗𝑏𝑚𝑖−118∗𝑐ℎ𝑖𝑙𝑑𝑟𝑒𝑛+.34∗𝑠𝑚𝑜𝑘𝑖𝑛𝑔−.1∗𝑟𝑒𝑙𝑖𝑔𝑖𝑜𝑛+.00095∗𝑐ℎarg𝑒𝑠 1 + −0.67667323 − .02 ∗ 𝑎𝑔𝑒 − .164𝑠𝑒𝑥 + .08 ∗ 𝑏𝑚𝑖 − 118 ∗ 𝑐ℎ𝑖𝑙𝑑𝑟𝑒𝑛 + .34 ∗ 𝑠𝑚𝑜𝑘𝑖𝑛𝑔 − .1 ∗ 𝑟𝑒𝑙𝑖𝑔𝑖𝑜𝑛 + .00095 ∗ 𝑐ℎarg𝑒𝑠

17. Steps involved in logistic regression Step 1: Import the required module Step 2: Generate the data set Step 3: Visualize the data Step 4: Split the data set Step 5: Perform logistics regression Step 6: Make predictions using algorithms Step 7: Display the confusion matrix

18. Sample code of Logistics regression

19. Admission Prediction Using LR 20 There are two possible outcomes: Admitted (represented by the value of ‘1’) vs. Rejected (represented by the value of ‘0’). We can then build a logistic regression in Python, where: The dependent variable represents whether a person gets admitted; and The 3 independent variables are the GMAT score Grade Point Average ( GPA ) Years of work experience

20. Applications of Machine learning in operations management Demand Forecasting Supply Chain M anagement Inventory, Warehouse and Logistics Management Waiting time in health care sector Risk Management Digital Marketing Scheduling Problems Predictive Maintenance Quality Control Product Development