Concept explainers
Explanation of Solution
Data Mining:
Data Mining is the extraction of knowledge and data patterns from various raw data sets by examining patterns, trends and other Business Intelligence reports using intelligent methods for classification and prediction.
- Data mining techniques differ from reporting applications, as they are very sophisticated and complex, hence difficult to use.
Difference of factors for reporting and data mining:
Factors | Reporting | Data mining |
Type of objective | Assessment | Prediction |
Company | Target | Netflix |
Analysis | Simple-summing, totaling | Advance statistics |
Types | Noninteractive – RFM, Interactive - OLAP |
Cluster Regression Market basket Decision tree Others |
Artificial Intelligence (AI) is the ability of machines to perform activities that require human intelligence. In AI, machines can have vision, and can perform communication, recognition and learning. In AI, machines also have the ability to make decisions.
Benefits:
- Dealing with heavy and mundane tasks become easier with the help of machines.
- In order to gather and analyze Big Data, AI is extremely useful to improve efficiency.
- AI will potential increase cyber security and improve the security of Internet of Things (IOT).
- The accuracy of working on a thing increases a lot with AI.
- Using AI the use of digital assistants will increase which in turn will decrease the need for human resources.
Difference between Data Mining and Machine Learning:
Data Mining | Machine Learning |
Data Mining is the extraction of knowledge and data patterns from various raw data sets by examining patterns, trends and other Business Intelligence reports using intelligent methods for classification and prediction |
Machine Learning uses various data mining techniques to extract knowledge from data based on |
In order to find patterns among data, Statistics and other | Based on the previously known training data, one can predict the outcome using Machine learning. |
Data Mining uses both Math and programming methods but inclination toward maths is more. | Machine Learning uses Data Mining techniques to build models that mostly use programming more than maths. |
Data mining techniques are difficult to use:
Curse of Dimensionality:
The Curse of Dimensionality is the observation that is observed that problem arises when one analyses and organizes the data in high dimensional spaces. Working with data becomes more demanding with increase with increase in dimensions.
- With the increase in number of attributes, there is more chance to build easily a model to fit all the sample data but as a predictor it is useless.
- In data mining analyses, having too many attributes is problematic as one of the major activities in Data Mining concerns efficient and effective ways of selecting attributes.
- The amount of data used for Data Mining is huge and one needs to reduce the volume the data in order to meaningfully analyse the data.
Difference between Supervised and Unsupervised Data Mining:
Unsupervised Data Mining | Supervised Data Mining |
In Unsupervised Data Mining, before running the analysis, analysts do not create a model or hypothesis. | In Supervised Data Mining, before running the analysis, data miners create a model and apply statistical techniques to the data. |
Cluster analysis is a technique that uses Unsupervised Data Mining | Regression Analysis is a technique that uses Supervised Data Mining. |
Cluster Analysis:
- Cluster Analysis is a way of arranging data such that data having similar properties are grouped together in a cluster. It is also known as clustering.
Example:
- Using Cluster Analysis, one can find patients with similar diseases from medicine history and demographic data.
Regression Analysis:
Data mining analysis which processes the consequence of a set of variables on other variables is called a regression analysis...
Want to see the full answer?
Check out a sample textbook solutionChapter 9 Solutions
Using MIS (10th Edition)
- How might data literacy be applied to the workplace or to ethical decision-making?arrow_forwardwatch the following videos from the YouTube channel StatQuest:● Machine Learning Fundamentals: Sensitivity and Specificity● ROC and AUC, Clearly Explained!After reading and watching those videos, you should write a short essay that answers the followingquestions in your own words:● What is precision, recall, sensitivity, and specificity? How would you explain it to someone new tothe field of machine learning?● What is the precision/recall trade-off? Provide an unique example to illustrate the concept.● Explain the ROC curve and how it is used.arrow_forwardWhat are the connections between data literacy and the world of work and ethics?arrow_forward
- Subject - Data Science 1) what is Attention based neural networks, classification and methodologies for sentment Anylysis. Thank in advancearrow_forwardA quick summary of the regression and Artificial Neural Network (ANN) model development processes.arrow_forwardSelect a problem that has national significance and can be solved using a machine learning approach. Describe the problem in 150-250 words Describe why this problem is an important problem Describe why you think this problem can be solved using a machine learning approach. Which machine learning approach is better for this problem and why? List the sequence of steps that you would use in order to solve this problem using machine learning.arrow_forward
- Fundamentals of Information SystemsComputer ScienceISBN:9781337097536Author:Ralph Stair, George ReynoldsPublisher:Cengage Learning