Data Mining I — DU B.Sc. (Hons) Computer Science Previous Year Question Papers

Use the Naive Bayes classification rule to classify a Red Domestic SUV. Show all the steps involved in the process which include calculating prior probabilities, conditional probabilities, and posterior probabilities and comparing the posterior probabilities. (b) Differentiate between bagging and boosting ensemble techniques with suitable examples. 1 Discovery (DSE-5) 2. The paper has two sections. 5. Parts of a question must be answered together. 1. (i) Indicate whether the following activities can be identified as a Data Mining Task or a Database (a) Calculating the revenue for each product category from sales data. (b) Predicting the future stock price of a company using historical data. : (c) Generating a list of all students who have 12th standard percentage higher than 80. (d) Clustering customers into different groups based on their buying patterns to target marketing campaigns more effectively. (ii) Determine the attribute type of the following: Use the k-Nearest Neighbor (k-NN) classifier with K = 5 and proximity measure as Euclidean distance to classify a test record (A = 5, B = 5). Which class would the k-NN classifier assign to the test record? 7. (a) Consider the following training data set for car theft: (10) Sample No. Color Type Origin Stolen? 1 Red Sports Domestic Yes 2 Red Sports Domestic No 3 Red Sports Domestic Yes 4 Yellow Sports Domestic No 5 Yellow Sports Imported Yes 6 Yellow SUV Imported No 7 Yellow SUV Imported Yes 8 Yellow SUV Domestic No 9 Red SUV Imported No 10 Red Sports Imported Yes Compute the Gini index for the overall collection of training data. Compute the Gini index for attribute A and B. Which attribute would the decision tree algorithm choose for the split at the root node? Give reason. (b) Consider the following dataset, which consists of 10 records, with two features, A and B, and a binary target class Z. (7) (a) Calender Year such as 2000, 2010, 2020, (b) Payment methods such as "cash", "credit card", "debit Card". (c) Speed such as 5 km/h, 10 km/h, 50 km/h, (d) Severity of Disease such as "mild", "moderate", "severe". (iii) What is the difference between predictive tasks and descriptive tasks? (2) (iv) What is the difference between noise and outlier? List any two ways to handle the missing values. (3) (v) What is the difference between model overfitting and model underfitting? (3) (vi) How is an eager learner classifier different from a lazy learner classifier? Support your answer with an example from both category of classifiers. (3) (vii) Consider the following data for the feature 120, 40, 10, 30, 60, 100, 200, 300, 400], Discretize the data into three bins using the equal width and equal depth approach. (vili) Suppose an attribute marital status has three distinct values {single, married, divorced}. Illustrate the three different ways to perform attribute test condition for the binary split. Also perform for the multiway split. (3)