Dears,, I want answers for these questions (not writen by hand please): 1) Selec

Question

Dears,,

I want answers for these questions (not writen by hand please):

1) Select two application areas for data mining NOT discussed in the text book and briefly discuss how data mining is being used to solve a problem (or to explore an opportunity)?.

2)What is Association Rule Mining? And explain how Market-basket analysis helps retail business to maximize the profit from business transactions?

3)Discuss k-nearest Neighbor (KNN) learning algorithm. What is the significance of the value of k in k-NN.

4)Discuss the two estimation methods of classification-type data mining models while considering ANN as a classifier.

Explanation / Answer

Q1-Two application areas for data mining

1-Retail Business-

Data Mining has its nice application in Retail business as a result of it collects great amount of information from on sales, client buying history, product transportation, consumption and services. it's natural that the number of information collected can still expand chop-chop attributable to the increasing ease, handiness and recognition of the net.

Data mining in retail business helps in distinguishing client shopping for patterns and trends that cause improved quality of client service and sensible client retention and satisfaction. Here is that the list of samples of data processing within the retail business –

• Design and Construction of information warehouses supported the advantages of information mining.

• Multidimensional analysis of sales, customers, products, time and region.

• Analysis of effectiveness of sales campaigns.

• Customer Retention.

• Product recommendation and cross-referencing of things.

2-Biological information Analysis-

In recent times, we've got seen an amazing growth within the field of biology like genetic science, proteomics, genomics and medicine analysis. Biological data processing could be a important a part of Bioinformatics. Following ar the aspects within which data processing contributes for biological information analysis –

• Semantic integration of heterogeneous, distributed genomic and proteomic databases.

• Alignment, indexing, similarity search and comparative analysis multiple ester sequences.

• Discovery of structural patterns and analysis of genetic networks and macromolecule pathways.

• Association and path analysis.

• Visualization tools in genetic information analysis.

Q2-Association Rule Mining-

Association rules ar if/then statements that facilitate uncover relationships between on the face of it unrelated information in an exceedingly info service} or different information repository. Associate in Nursing example of Associate in Nursing association rule would be "If a client buys a dozen eggs, he's eightieth seemingly to conjointly purchase milk."

An association rule has 2 elements, Associate in Nursing antecedent (if) and a ensuant (then). Associate in Nursing Associate in Nursingtecedent is an item found within the information. A ensuant is Associate in Nursing item that's found together with the antecedent.

Association rules ar created by analyzing information for frequent if/then patterns and exploitation the factors support and confidence to spot the foremost vital relationships. Support is a sign of however oft the things seemwithin the information. Confidence indicates the amount of times the if/then statements are found to be true.

So,Based on the higher than of milk and egg milk corporations uses these information of Market-basket analysis so as to maximise the numbers of milk packets oversubscribed

Q3- K-nearest Neighbor (KNN)-

K-nearest neighbors could be a classification formula, that could be a set of supervised learning. K-means could be a bunch formula, that could be a set of unsupervised learning. the closest neighbour formula was one among the primary algorithms wont to confirm an answer to the traveling salesman drawback. In it, the salesperson starts at a random town and repeatedly visits the closest town till all are visited. It quickly yields a brief tour, however typically not the optimum one.KNN are often used for each classification and regression prophetical issues. However, it's additional wide employed in classification issues within the business. to guage any technique we tend to typically examine three vital aspects:

1. Ease to interpret output

2. Calculation time

3. prophetical Power

In KNN, finding the worth of k is vital task. atiny low worth of k means noise can have the next influence on the result and an oversized worth build it computationally dear.

Q4-The two estimation strategies of classification-type data processing models-

1-A multilayer feedforward neural network is Associate in Nursing interconnection of perceptrons within whichinformation and calculations flow in an exceedingly single direction, from the input file to the outputs. range|the amount|the quantity} of layers in an exceedingly neural network is that the number of layers of perceptrons. the best neural network is one with one input layer Associate in Nursingd an output layer of perceptrons. Technically, this can be named as a one-layer feedforward network with 2 outputs as a result of the output layer is that thesolely layer with Associate in Nursing activation calculation.

2-The backward propagation of errors or backpropagation, could be a common technique of coaching artificial neural networks Associate in Nursingd employed in conjunction with an optimisation technique like gradient descent. The formula repeats a 2 section cycle, propagation and weight update. once Associate in Nursing input vector is given to the network, it's propagated forward through the network, layer by layer, till it reaches the output layer. The output of the network is then compared to the required output, employing a loss perform, and a slip-up worth is calculated for every of the neurons within the output layer. The error values ar then propagated backwards, ranging from the output, till every nerve cell has Associate in Nursing associated error worth that roughly represents its contribution to the first output.

Related Questions

Navigate

• Browse (All)
• Browse D
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.