Data Mining and AI: Can Automated Mining Processes be Achieved?

The assignment will answer the question: is there any chance for data mining to be carried out by AI (automated)?

The respond should answer the above question

• The respond should be 250 – 300 words
• With Harvard reference

I put the initial post by the student that we need to respond to and one example that other user already responded, so could the expert answer the above question on the similar style that other student respond to the below initial request.

Data Mining:

Data Mining is the generation of new information based on a massive investigation process in a large data bank. Intuitively, it is not picking new data from the raw data available, but it is extrapolating new knowledge, trends, and patterns out of the collected data (Han et al., 2011).  

Based on the technologies and techniques out of the intersection of database management, machine learning, and statistics, the scientists in data mining draw their path to understand the processing and drawing conclusions operations from a bulky amount of information (Hastie et al., 2009).

Data Mining Techniques:

• Clustering:it is the same as the classification, but with grouping chunks of data based on similarities, like gathering people of different demographics into groups(packets) based on their incomes.  
• Outlier detection: the recognition of the overarching pattern not giving directly a full understanding of the data set. The anomalies have to be identified as when your buyers are always females, and in one week, the spike turns to be men buyers.
• Tracking patterns: which is the ability to understand to identify the patterns in the data sets. Typically, it is an aberration in data that occurred regularly like sales increase before holidays.
• Classification: which is a complex technique, where all the different attributes collected together in a discernable way to draw further conclusions like performing an assessment of data for individual customers financial backgrounds and the purchasing history.
• Regression: it is a tool of planning and modeling, and suitable to identify the likelihood of a specific variable due to existing of another variable, like fixing prices of a product based on the availability, demand, and competition.    
• Association: These are the tracking patterns with more dependently linked variables. Because of that, the focus will be diverted on special events or attributes having a high correlation with others like when customers buy an eyeglass, they buy a hat as a related item.
• Prediction: it is a powerful tool in analysing because of its ability to project the data types expected in the future like customers credit histories and past purchasing transactions.

The Pros of Data Mining are the forecasting market trends, attract and retain customers, anomaly detection with more accurate analysis, better customer relationship management, and helps stay ahead of the competition. The cons of data mining are the data mining violates user privacy, lack of precision or incorrect information, expensive in the the initial stage, and security of the critical data (Olson, 2007).

Finally, in the contemporary changing business environment and abundance of big data scattered everywhere, it is hard to find the needed data for your purpose. Therefore, the practicing of data mining is a crucial tool to minimise the processing of analysis and pick the relevant information (Kantardzic, 2011). On the contrary, there is a limitation to where this going beyond, in simple words, if the advantages of the carried-out analysis are more outweigh the disadvantages, no need to do repeat the analysis.

I distinguished attract and retain customers and the stay ahead of the competition as positives, and security of the critical data and expensive in the initial stage in my former project management company; Morganti Inc.