Information Loss characteristics in Privacy preservation approach using anonymization approach
V Shashidhar, R Vikshitha, Raksha Umashankar · 2023
Significant concerns have been raised by the growing digitization of personal data about individual privacy in data mining applications. This research paper presents an approach to address this privacy challenge by leveraging the concept of k-anonymity in reference to data mining. Our study introduces a Python-based framework that focuses on improving the privacy of sensitive information during the data mining process. The development and evaluation of a workable strategy for improving privacy in data mining is the main goal of this study. We start out by giving a detailed evaluation of the limits of the current privacy preserving methods. Then, we extend the k-anonymity model’s applicability to data mining by putting forth a Python-based implementation of this tried-and-true privacy preservation method. Our approach makes sure that a collection of k records cannot be used to identify a specific record, protecting the confidentiality of critical information. The research paper includes a detailed discussion of the design and architecture of the Python-based k-anonymity system, which integrates seamlessly into various data mining algorithms and workflows. We present experimental results and comparative analyses to demonstrate the effectiveness of our approach in improving privacy while maintaining the utility and accuracy of data mining results. We assess the trade-offs between privacy and data utility, providing insights into parameter tuning for optimal performance. In conclusion, our research contributes to the ongoing efforts to protect individual privacy in data mining by introducing a novel, Python-based k-anonymity approach. This paper offers a significant step towards bridging the gap between data mining’s analytical power and the protection of personal information, making it an invaluable tool for educators, qualified individuals, and institutions aiming to ensure data privacy compliance while deriving valuable insights from their datasets.