Business intillegence question

What are the privacy issues with data mining? Do you think they are substantiated?

Nandinii Alla Post

Privacy Issues in Data Mining

Introduction

It is paramount that when data is a considerable amount, it becomes difficult for the same data users to derive valid and sound conclusions from it. Therefore, it is essential to extract the most crucial data from the original data's vast set. The process of extracting useful data from an extensive raw data set is known as data mining. There are various benefits associated with data mining (Zhang, Jang-Jaccard, Qi, Bhuiyan & Liu, 2018). For instance, data mining makes the decision-making process more manageable, aid in detecting any fraud, and promoting the prediction of trends in the future. It is also important to note that there are some privacy issues associated with data mining. To this extent, therefore, this discussion seeks to discuss various privacy issues related to data mining.  

Privacy issues with data mining

Data tends to be the most sensitive information that most of the businesses stores. The goal of every profit-making organization is to maximize profits and reduce the costs as much as possible. For this to happen, different means are used to ensure that these organizations remain competitive. One of them is the protection of data from outsiders, such as competitors. There are various issues related to the privacy of data that affect most businesses. They include access controls, filtering and validating external sources, updating non-verified data, and security architect evaluation. The following are some of the privacy issues associated with data mining (Chamikara, Bertók, Liu, Camtepe & Khalil, 2020).

Access controls

Access controls are crucial in the identification of the users of the data. They help limit the number of persons within an organization who can access sensitive and confidential data and information. However, these access controls are not entirely reliable at times, which is a privacy issue in data mining (Shah & Gulati, 2016).

Update of data which is not verified

It happens that in most organizations, data is collected and updated in the systems without verifying the source of the files with the data. This seems to be a lapse in security, which can cause adverse effects to the organization in one way or another (Zhao, Ni, Hu, Chen, Zhou, Xiao & Wu, 2018, April).

Filtering and validating external sources

It is a matter of the fact that the systems' privacy may be compromised, especially when an unauthorized device connects to that system's security, thus making a provision of entry point for different susceptibilities. For instance, when persons take data related to the organization to their homes in the name of working may result in a loophole in the organization's data privacy (Xu, Jiang, Chen, Wang & Ren, 2016).

 

Conclusion

In conclusion, therefore, it is evident that various privacy issues in data mining are substantiated. Concerns related to data privacy have grown to be an essential issue in the mining of data. Organizations are adopting different means to protect data and information, but some of these methods are also vulnerable to attacks. To this end, businesses should implement other forms of data protection to solve some of the privacy concerns in data mining.

 

  

References

Chamikara, M. A. P., Bertók, P., Liu, D., Camtepe, S., & Khalil, I. (2020). Efficient privacy preservation of big data for accurate data mining. Information Sciences, 527, 420-443.

Shah, A., & Gulati, R. (2016). Privacy-preserving data mining: Techniques classification and implications—A survey. Int. J. Comput. Appl, 137(12), 40-46.

Xu, L., Jiang, C., Chen, Y., Wang, J., & Ren, Y. (2016). A framework for categorizing and applying privacy-preservation techniques in big data mining. Computer, 49(2), 54-62.

Zhao, L., Ni, L., Hu, S., Chen, Y., Zhou, P., Xiao, F., & Wu, L. (2018, April). In private digging: Enabling tree-based distributed data mining with differential privacy. In IEEE INFOCOM 2018-IEEE Conference on Computer Communications (pp. 2087-2095). IEEE.

Zhang, X., Jang-Jaccard, J., Qi, L., Bhuiyan, M. Z., & Liu, C. (2018). Privacy issues in big data mining infrastructure, platforms, and applications.

 

REPLY POST

What are the privacy issues with data mining? Do you think they are substantiated?

Rashmi Thota 

COLLAPSE

Top of Form

Data mining is researching and analysing big data in order to find concrete patterns and laws. It is considered a specialty within the area of analysis of data science and is distinct from predictive analytics because it represents past data, whereas data mining attempts to forecast future results. Data mining techniques are also used to create machine learning (ML) models that control modern art models guiding current AI applications, such as search engine algorithms and recommendation systems. The first step of data mining is business understanding. It involves collection of the data required, areas to be concentrated, deadline of the project, boundaries of the project and the concern of the project.

 The second step is data understanding which involves collection of data from all the sources which may be raw data and looks totally complex. There comes the third step which is data preparation. It involves Data is then filtered, and it contains lost data to ensure that it is able to be mined. Depending on the volume of data analysed and the number of data sources, data analysis can take massive quantities of time and then followed by other steps which involves data modelling, evaluation and development, where, analysed data is put into mathematical modelling and evaluating the steps and develop the project. (Han, Kamber, & Pei, 2011) The big data problems are pervasive, invading any area that captures, stores, and analyses data. Big data faces four main challenges: number, range, veracity and time. Data mining 's aim is to mediate certain difficulties and unlock the usefulness of the results

. This large volume of data poses two big challenges: first is identifying the right data is more challenging, and second is reducing the processing speed of data mining techniques. Variety covers the various different types of captured and preserved data (Segaran, 2007). The data mining applications need to be designed to handle a wide variety of data formats simultaneously. The increased data storage demand has prompted several businesses to turn to cloud computing and storage. While the cloud has enabled many technological advancements in data processing, the infrastructure structure poses major challenges to privacy and security. To retain the trust of their associates and clients, organisations must protect their data from malicious individuals.

REFERENCES

Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (The Morgan Kaufmann Series in Data Management Systems) (3rd ed.). Morgan Kaufmann.

Segaran, T. (2007). Programming Collective Intelligence: Building Smart Web 2.0 Applications (1st ed.). O’Reilly Media.

REPLY POST: