On this page, you will find Most important and Mostly asked previous year questions in your b tech semester exam from unit 4 Classification and Clustering of the subject Data Warehouse and Mining.

### Questions

- Write a note on classification and clustering.
- Discuss why analytical characterization and attribute relevance analysis are needed.
- Describe statistical measures in large database.
- With the help of suitable example, explain data discrimination in brief.
- Given the following set of value [1,3,9,15,20]. Determine the Jack knife estimate for both the mean and standard deviation the mean.
- Write and explain statistical-based algorithm.
- What are the main purpose of statistic used in data mining?
- Explain simple approach of distance based algorithm.
- Write a short note on decision tree based algorithm.
- Explain K nearest neighbours in context to distance based algorithm.
- Write a note on prediction and classification.
- What are different classification techniques? Discuss issues regarding classification and prediction.
- Describe various issue regarding classification and prediction.
- Explain the algorithm for classification by decision tree induction.
- What do you mean by decision tree? Describe ID3 algorithm of the decision tree. Why it is unsuitable for data mining application.
- Describe classification. Briefly outline the major ideas of Bayesian classification.
- What is Naive Bayesian classification ? Why is Naive Bayesian classification called “Naive” ?
- What is clustering ? How is this different from classification ? Explain any one approach for clustering.
- Write the advantage and disadvantage of clustering.
- Explain the data type that often occur in cluster analysis and briefly explain how to preprocess that data for clustering?
- Discuss the various approach of clustering.
- Explain the various requirements of clustering in data mining.
- Write a note on agglomerative hierarchical clustering .
- Write a note on partitioning methods.
- Explain the k-mean clustering algorithm.
- Explain the Nearest neighbor algorithm.
- Explain Squared error clustering algorithm.
- Explain Partitioning around methods (PAM) algorithm.
- Explain Chameleon hierarchical clustering.
- Write the basic difference between clustering and classification. Describe the density-based clustering method based on connected regions with sufficiently high density (DBSCAN).
- Write short notes on STING.
- Write a short note on OPTICS density-based clustering.
- Describe CLIQUE algorithm.
- Explain market basket analysis . Describe the concept of association rule mining.
- Describe the mining single dimensional boolean association rules from transactional database.
- Describe the Apriori algorithm for FIM (Frequent Itemset Mining) and verify it through suitable example.
- Why is the task of mining frequent item sets difficult? Explain the reasons.
- Explain the mining multidimensional association rules from relational databases and data warehouse.
- Describe the Apriori algorithm : Finding frequent item sets using candidate generation.
- Explain mining multilevel association rules from transactional databases.
- What do you mean by neural network? Explain multiplayer feed-forward neural network. Differentiate between feed-forward and feedback system.
- Describe neural network . How the neural network is useful in classification ? Explain.
- Q35). Write a note on Backpropagation algorithm.