Introduction to Data Mining

Data mining is a process by which hidden data are extracted or discovered from a large dataset stored in the large database management system called the data warehouse. Data can be extracted through the use of some specific techniques like carrying out statistical research, embracing machine learning or artificial intelligence. For one to be able to extract the required data from the repository site, data mining skills are required.

Data mining is being relied on by various business industries just ensure uniform growth and efficiency of the industry. Thus there is need to ensure that data mining process has to be standardized.

Data mining processes has to be improve day by day. This is done through a research where users are being interviewed on the functionality of the current system. Since data mining is a continuous growing process that keeps changing with time.

3.0 Methodologies

3.0.1Data generation. This is the process where data are established and analyzed. After the data has been collected, they are analyzed using the data analysis tools such as the machine learning and the artificial intelligence. During analysis process, it very prudent to filter some very sensitive data to avoid issues to do with security. For security reasons, some data are filtered and made secure before storing them in the data mining server. The data mining server is the repository site which contains all the data to be extracted.

3.0.2Business understanding. This is the phase where we have to understand the current business fully and the objective of the business are laid out clearly and the needs of the business are supposed to be found. The existing business behavior must be assessed. Resources, assumptions, and constraints are taken into account. From there we have to establish the data mining goals to ensure the objective of the business are achieved. The goal of reconciliation is to ensure that a good data mining plan is created.

3.0.3Data preparation. It takes a lot of time to do data preparation. Data preparation implies analyzing those data and grouping them together according to how they relate. It provides the final data to be stored in the data warehouse. The data collected are filtered and clean at this phase so that the sensitive data are made secure and unnecessary data are disposed.

3.0.4Data modelling. A data mart is designed which include the conceptual design for checking the dimensions and facts about the business process model. The techniques to be used in data modelling has to be chosen so as to be used to prepare the dataset. The model is tested for its validity and quality to meet the business requirements.

Data Mining Techniques

3.0.5 Model evaluation. In this stage, the data are studied and analyze so that the actual data required are gathered. The actual system need to be studied very well and understood. New ideas regarding the business are raised so that the new techniques which have been explored are up to the task. In this stage, it is where decision is made whether or not the business process will continue.

3.0.6 Report and decision making. The decision is made after all the processes have been passed and an implementation of the new ideas is set to action. The stakeholder come up with a full report of all the processes done during the business model process. The processes of implementation, monitoring and maintenance has to be created.

The figure below is a design process to show all the process steps that are required during data mining business process scheduled

Figure 1.0 describes the six processes through which the data has to pass through before implementation. In each stage, the stakeholders have to discuss about the requirements for the startup of the business. As shown in the figure 1.1 above every process or the stage is discussed in detail so that they come to an agreement first before they implement the project. The data are generated through collection and then they are studied and analyze. This data can be analyze by use of interviews and creating questionnaires so that people have to answer some questions (Anon, 2018). Data security concerns are discussed in every stage so that the privacy of the business is kept. Some of the data are filtered (these are the sensitive data that might affect the behavior and functionality of the business model.

In this research of the business model, the methodology used to research is the waterfall method. This is a step by step procedure to reach a specific target goal. The end of analysis of all the data collected a report is generated so that it can help to reconcile the stakeholders agreement and will allow the immediate implementation of the data mining project. Maintenance and monitoring team is setup to enhance the proper working of the system.

The goal of NORA (Non-Obvious Relational Awareness) is to give  scholars a workspace for exploring the system-identified features of common documents and further documents that havebeen recommended by the system. Each of these projects is discussed within the framework of visualizations involving browsing through dynamic grouping.

The Importance of Data Mining Processes

The function of NORA is to give scholars a space to work on discovering the kind of system identified features of the important documents. It has been recommended by the system to process some functional inputs. The NORA project is normally discussed within the system framework of visualizations involving internet search through grouping the data.

ANA (Anonymized Data) is another technique used to filter data which are encrypted during data mining process. It ensures that the retrieved data are safe and are relevant to the user. Normally ANA is used to ensure that data security is kept and is well protected.

As-Is and To-Be process is typical of one cycle since if follows the system that we must follow the way in which we need to study the SWOT analysis process through which we analyze the strengths, threads, opportunities and weaknesses. The process is clearly shown in this diagram.

The cost of To-Be process is much higher since it requires the inputs which deliver the intellectual product. Input cost for this process is very high and therefor it is very expensive.

Conclusion

Data mining techniques and processes have greatly played an important role in the field of business implementation. It provides a clear outline on how the program of the business is going to be implemented. Therefore researches have shown that data stored in a very large database, have helped business firm when they are doing some research about what they need to do. BPMN (Business process modelling notation) is a tool that makes it easier for various organization to plan what they are supposed to do in a series of stages. This means that a certain methodology has to be followed. Specifically, waterfall is the best to be used in the reengineering for the data mining process model.

References 

Burcu Uçel, E. and Katrinli, A. (2014). A Qualitative Inquiry from the Aegean Region: Changing Ruling Clas in Busines Circles. bilig, Journal of Social Sciences of the turkish World, (71), pp.247-268.

Stein, S., Hamilton, B., Peterson, T., Guyer, C., 2016, Develop using Always Encrypted with .NET Framework Data Provider. [Online] Available at: https://docs.microsoft.com/en-us/sql/relational-databases/security/encryption/develop-using-always -encrypted-with-net-framework-data-provider (Accessed 24 October. 2017)

Prasad, V., Ramdevputram A., 2015, “Identifying the Networks of Criminals Using Management Information System”, International Journal of Innovations & Advancement in Computer Science, vol.4, Special Issues, pp. 144-148.

Ramos-Merino, M., Santos-Gago, J., Álvarez-Sabucedo, L., Alonso-Roris, V. and Sanz-Valero, J. (2018). BPMN-E2: a BPMN extension for an enhanced workflow description. Software & Systems Modeling./5-real-life-applications-of-data-mining-and-business-intelligence/ [Accessed 9 Sep. 2018].

Solaimani, S. and Bouwman, H. (2012). A framework for the alignment of business model and business processes. Business Process Management Journal, 18(4), pp.655-679.