Answer 1List 5 data mining things learned in class and how they apply.Unsupervised machine learning is used when t

Answer 1

List 5 data mining things learned in class and how they apply.

1. Unsupervised machine learning is used when there is no class labels associated with the data (Tan et al., 2019). Clustering is often used here. This would be helpful to search through customer help desk ticket comments or customer relationship management text.
2. Supervised machine learning is used when the data already has class labels. The labels are used to classify the data (Tan et al., 2019). Supervised machine learning often produces better results in general, than unsupervised machine learning. This would be good for sorting spreadsheet or database data in different ways to see different things.
3. Anomaly detection is useful to find the outliers (Tan et al., 2019). Anomaly detection algorithms are likely being used in our IDS systems and firewalls at work. Also, anomaly detection is helping keep my credit cards safe from fraud.
4. Association analysis and in particular, market basket analysis seems to be pervasively used a lot more than I realized prior to this class. Association analysis algorithms are likely what is being used by Amazon, Facebook and Google to see our patterns of what we search on, click on, or purchase.
5. Statistics can help hide those false discoveries or present them front and center, depending on the goal. Now I am going to be curious every time I see research data, as to what statistical method they used.
6. Lastly, I discovered this RapidMiner COTS software for data mining, that I am curious about and wish we had at my work. Has anybody in the class ever used this software product ?

It has been fun in this learning journey with all of you. Wishing everybody the best of luck in your higher education and careers! Virtual high-fives to everybody!

Take care, all!

Lisa King

Reference:

Tan, P., Steinbach, M., Karpatne, A., & Kumar, V. (2019). Introduction to Data Mining (2nd Edition). Pearson Education (US).

—————————————————————————————————————————————-

Answer 2

Data Mining:

Data mining is a method of separating data to identify examples, styles, and auxiliary nuances that allow it to be settled on a data-based option on substantial data sets. All in all, we can say that dining mining is a course that examines stocked data designs in different ways that separate valuable data, which is collected and coordinated in clear areas such as data stores, investigation, data mining calculation, dynamic and additional data. Eventually, costs and adaptation need to be reduced.

Data mining is a natural-looking display to find styles and examples that directly cross the cycles of insight for enormous data stores. Data mining utilizes complex numerical methods in data segments and explores the possibilities in future cases. Data mining is called data collection information (KDD).

Data mining is a cycle used by associations to extract specific data from extensive scope data to solve business problems. It will inevitably turn into valuable data on crude data. Data mining is like artificial data science, in a particular context, on a specific data set, for a reason. This interaction includes administrations: text mining, web mining, sound and video mining, picture data mining, and correspondence mining. This is done with basic or explicit programming. With data-mine extraction, every task is possible faster with lower work costs. Companies are unique and can use new advances to collect data that is physically difficult to obtain. Extensive data is available at various stages. However, very little data is available. Data research is the most critical test to distinguish essential data that can be used to track problem or organization progress. There are many valuable assets and policies available in mining data, and you can improve its understanding. (Naouma, P. (2019))

Types of Data Mining:

Data mining can be done on the following types of data:

Related Websites:

A related website is an assortment of multiple data sets integrated into tables, records, and sections, where data can be retrieved in various ways without having to look at data tables. Tables are moved, and data is provided, including data search, details, and requests.

Data Warehouse:

The Data Warehouse is an innovation that collects data from various sources within the Association to provide essential business ideas. Many data comes from many sources, such as marketing and finance. The extracted data is used for analytical purposes and aids in business dynamics and is intended for data research instead of database exchange management.

Data Archives:

Data archives usually refer to a data storehouse. However, many IT professionals will undoubtedly refer to this term as a specific setting within the IT structure. For example, a data bunch in which the Association stores an assortment of data.

Related data:

The combination of a specific article model and the relevant data model is called an item-related model. Supports classes, topics, heritage, and so on.

One of the fundamental reasons for the object-social data model is to close the gap between the relational database and the item-based model practices used in many programming dialects, for example, C ++, Java, C #, etc.

Interaction Database:

The transaction database refers to the Data Framework (DBMS), which can delay data exchanges if not managed effectively. Although it has had an exciting potential, most social database frameworks today support conversion data operations. (Tatti, V. (2012)).

Advantages of Data Mining:

• Empowers data mining measurement associations to obtain data based on data.
• Data mining empowers associations to execute productively and efficiently.
• In contrast to different data applications, data mining saves costs.
• Data mining works with the dynamic interaction of the Association.
• Works with projected examples and programmed position of models and practice estimates.
• It will be added to the new framework just like the existing steps.
• This is a quick method to make it easier for new clients to break many data in a short period.

Disadvantages of Data Mining:

• There are openings for associations to provide valuable client data to various associations for a charge. According to the report, American Express sold its client purchases to various communities through their clients.
• Many mining exam programming is complicated to use, and you need to be prepared in advance to get out of it.
• Different data mining devices work in different ways due to different calculations used in their development. Consequently, choosing the right data mining tools is a very challenging assignment.
• Data mining strategies to prompt adverse outcomes in specific situations are unclear.

Reference:

Tatti, V. (2012). Comparing apples and oranges: measuring differences between exploratory data mining results. Data Mining and Knowledge Discovery, 25(2), 173–207

Naouma, P. (2019). A comparison of random-field-theory and false-discovery-rate inference results in the analysis of registered one-dimensional biomechanical datasets. PeerJ (San Francisco, CA), 7, e8189–e8189.