What are the privacy issues with data mining? Do you think they are substantiated?. Reply to post 1 Data mining can be expensive, and it takes time to conduct it. Some businesses run on big data platforms like Microsoft's Cortana. Big data companies also have a high risk (Roiger, 2017). There is a risk that the machines themselves could hack. There is a risk that the data-mining company might misappropriate data or sell it out to third parties for profit. Data mining platforms can offer real solutions to problems like these. They can also provide accurate data or data directly related to the products and services they run. Data mining's main disadvantage is that it is costly; hence, it is not a very practical method in the early stages of data science. In the end, data mining is just the automated generation of hypotheses from data. The most significant data mining issues are that most data mining companies are often not very good at understanding natural human behaviors or human language. Most data mining companies will use natural language processing, natural language extraction, text classification, text analysis, and natural language inference. As a result, their approaches will not be excellent since they often do not understand why users do certain things. They will not get to the root of the problem, so most data miners are less efficient than humans at interpreting natural language (Tan et al., 2016). Data mining's significant difference is that many data mining companies use high-speed computers and high-class statistical methods. To conduct their data mining tasks compared to their data scientists, which tend to run these statistical methods on more expensive computers and high-end statistical programs. Data mining is a new and unique way of identifying an entire group of information. So, it’s also very difficult to detect as there are many unknowns on the network. As such, the data is considered less useful than data mining and is not as useful as other methods and techniques Reply to post 2 Data mining is the methodology used to obtain data to create a database that may be used by a variety of different methods for statistical evaluation, predictive predictions, or any other desired purpose. Data Mining is considered very accurate in identifying individuals. Data Mining can be used to locate a particular person in a large group of groups or track movements when an employee is on the go. Data Mining provides a more precise understanding of a person by combining multiple data sets. There are a few limitations to data mining. First, one must keep in mind the statistical limitations of the data, which are also the scientific method's limitations (Asif et al., 2017). For instance, if analyzing data from a large sample size with multiple possible causes, one can use correlation to confirm a link. However, correlation does not prove causation, nor does it mean all data points fall within a specific probability model. Data mining requires large samples in order to confirm a link. Second, data mining is more susceptible to selection bias. For instance, for a complex problem, researchers may not find the original problems or focus on those problems that are easier to solve for the researcher. Data mining is not very good at detecting anomalies outside the expected behavior of a data set. It is because normal variation is usually a direct correlate with the data set's actual structure, rather than an artifact outside the normal range of the data (Lu et al., 2017). Data mining is simply the process by which data is gathered and examined to understand how a particular topic behaves or will behave in the future.