Data mining privacy preserving: Research agenda

Kreso, Inda; Kapo, Amra; Turulja, Lejla

doi:10.1002/widm.1392

Cited by 23 publications

(7 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last decade bibliometric analysis has been used widely for analyzing content of citations within scientific material and to investigate the area of interest more closely (Kreso et al 2020). We use bibliographic analysis to consider the research areas, keywords, citation and co-citation networks, extract the most influential papers and authors, and identify the roots of the field.…”

Section: Results Of Bibliometric Analysismentioning

confidence: 99%

How Many Stocks Are Sufficient for Equity Portfolio Diversification? A Review of the Literature

Zaimović

Omanovic

Arnaut-Berilo

2021

JRFM

View full text Add to dashboard Cite

Using extensive and comprehensive databases to select a subset of research papers, we aim to critically analyze previous empirical studies to identify certain patterns in determining the optimal number of stocks in well-diversified portfolios in different markets, and to compare how the optimal number of stocks has changed over different periods and how it has been affected by market turmoil such as the Global Financial Crisis (GFC) and the current COVID-19 pandemic. The main methods used are bibliometric analysis and systematic literature review. Evaluating the number of assets which lead to optimal diversification is not an easy task as it is impacted by a huge number of different factors: the way systematic risk is measured, the investment universe (size, asset classes and features of the asset classes), the investor’s characteristics, the change over time of the asset features, the model adopted to measure diversification (i.e., equally weighted versus optimal allocation), the frequency of the data that is being used, together with the time horizon, conditions in the market that the study refers to, etc. Our paper provides additional support for the fact that (1) a generalized optimal number of stocks that constitute a well-diversified portfolio does not exist for whichever market, period or investor. Recent studies further suggest that (2) the size of a well-diversified portfolio is larger today than in the past, (3) this number is lower in emerging markets compared to developed financial markets, (4) the higher the stock correlations with the market, the lower the number of stocks required for a well-diversified portfolio for individual investors, and (5) machine learning methods could potentially improve the investment decision process. Our results could be helpful to private and institutional investors in constructing and managing their portfolios and provide a framework for future research.

show abstract

Section: Results Of Bibliometric Analysismentioning

confidence: 99%

How Many Stocks Are Sufficient for Equity Portfolio Diversification? A Review of the Literature

Zaimović

Omanovic

Arnaut-Berilo

2021

JRFM

View full text Add to dashboard Cite

show abstract

“…Existing privacy-preserving techniques used in data mining [13][14][15][16] and machine learning techniques [17][18][19] are data perturbation and cryptography. Reference 20 proposed a blockchain-assisted method to enhance security using Attribute-based searchable encryption (ABSE) of fine-grained searchable encryption in a cloud-based healthcare cyber-physical system.…”

Section: Related Workmentioning

confidence: 99%

Privacy‐preserving credit risk analysis based on homomorphic encryption aware logistic regression in the cloud

Divakar Allavarpu,

Naresh,

Krishna Mohan

2024

Security and Privacy

View full text Add to dashboard Cite

With the growing significance of Credit Risk Analysis (CRA) with a focus on privacy, there is a pressing demand for a Privacy Preserving Machine Learning (PPML) decision support system. In this context, we introduce a framework for privacy‐preserving credit risk analysis that utilizes Homomorphic Encryption aware Logistic Regression (HELR) on encrypted data. The implementation involves the use of TenSEAL and Torch libraries for Logistic Regression (LR), integrating the proposed HELR on polynomial degrees 3 and 5 across German, Taiwan, Japan, and Australian datasets. The presented model yields satisfactory results compared to non‐Homomorphic Encryption (HE) models, demonstrating a minimal accuracy difference ranging from 0.5% to 7.8%. Notably, HELR_g5 outperforms HELR_g3, exhibiting a higher Area Under Curve (AUC) value. Additionally, a thorough security analysis indicates the resilience of the proposed system against various privacy attacks, including poison attacks, evasion attacks, member inference attacks, model inversion attacks, and model extraction attacks at different stages of machine learning. Finally, in the comparative analysis, we highlight that the proposed model ensures data privacy, encompassing training privacy and model privacy during the training phase, as well as input and output privacy during the inference phase a level of privacy not achieved by existing systems.

show abstract

“…According to [12] data mining is a technique of examining data in a statistical perspective to extract relevant information about the data for informed decision making. It is a useful technique that enables an analyst to expose detailed information about data and enable users of the data to make predictions and projections on the data.…”

Section: Data Miningmentioning

confidence: 99%

Expert System in Enhancing Efficiency in Basic Educational Management using Data Mining Techniques

Inusah¹,

Missah²,

Ussiph³

et al. 2021

IJACSA

View full text Add to dashboard Cite

The importance of basic education is well noted in every country. Proper planning and utilization of resources at the basic level, helps in leveraging the success of education at all other levels of education in a country. Ghana is noted to be the country that spends higher in education than its West African counterparts. In Ghana, attempts made to plan by predicting and projecting expenditure as well as the available resources to manage basic education are not accurate enough to address the challenges of education in the country. With the issue of COVID 19 pandemic, more expenditure is realized in managing educational institutions as more resources are needed in observing the protocols to curtail the pandemic. This throws a serious challenge to the effective and efficient utilization of the limited resources in the country. In this paper, the data from the Ministry of Education is analysed using data mining techniques. This has helped to identify the inaccuracies in the data. Inaccurate population projection affects the Key Performance Indicators (KPIs) in education because population is a common denominator for educational indicators. A proposed expert system is to be developed to assist in managing the situation.

show abstract

Data mining privacy preserving: Research agenda

Cited by 23 publications

References 78 publications

How Many Stocks Are Sufficient for Equity Portfolio Diversification? A Review of the Literature

How Many Stocks Are Sufficient for Equity Portfolio Diversification? A Review of the Literature

Privacy‐preserving credit risk analysis based on homomorphic encryption aware logistic regression in the cloud

Expert System in Enhancing Efficiency in Basic Educational Management using Data Mining Techniques

Contact Info

Product

Resources

About