On Using Linear Diophantine Equations for in-Parallel Hiding of Decision Tree Rules

Data sharing among organizations has become an increasingly common procedure in several areas such as advertising, marketing, electronic commerce, banking, and insurance sectors. However, any organization will most likely try to keep some patterns as hidden as possible once it shares its datasets with others. This paper focuses on preserving the privacy of sensitive patterns when inducing decision trees. We adopt a record augmentation approach to hide critical classification rules in binary datasets. Such a hiding methodology is preferred over other heuristic solutions like output perturbation or cryptographic techniques, which limit the usability of the data, since the raw data itself is readily available for public use. We propose a look ahead technique using linear Diophantine equations to add the appropriate number of instances while maintaining the initial entropy of the nodes. This method can be used to hide one or more decision tree rules optimally.

Download Full-text

Using Minimum Local Distortion to Hide Decision Tree Rules

Entropy ◽

10.3390/e21040334 ◽

2019 ◽

Vol 21 (4) ◽

pp. 334 ◽

Cited By ~ 3

Author(s):

Georgios Feretzakis ◽

Dimitris Kalles ◽

Vassilios Verykios

Keyword(s):

Decision Tree ◽

Electronic Commerce ◽

Decision Trees ◽

Heuristic Approach ◽

Common Procedure ◽

Raw Data ◽

Binary Decision ◽

Local Distortion ◽

Binary Decision Tree ◽

Cryptographic Techniques

The sharing of data among organizations has become an increasingly common procedure in several areas like banking, electronic commerce, advertising, marketing, health, and insurance sectors. However, any organization will most likely try to keep some patterns hidden once it shares its datasets with others. This article focuses on preserving the privacy of sensitive patterns when inducing decision trees. We propose a heuristic approach that can be used to hide a certain rule which can be inferred from the derivation of a binary decision tree. This hiding method is preferred over other heuristic solutions like output perturbation or cryptographic techniques—which limit the usability of the data—since the raw data itself is readily available for public use. This method can be used to hide decision tree rules with a minimum impact on all other rules derived.

Download Full-text

Machine Learning Techniques Applied to Profile Mobile Banking Users in India

International Journal of Information Systems in the Service Sector ◽

10.4018/jisss.2013010105 ◽

2013 ◽

Vol 5 (1) ◽

pp. 82-92 ◽

Cited By ~ 8

Author(s):

M. Carr ◽

V. Ravi ◽

G. Sridharan Reddy ◽

D. Veranna

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Decision Tree ◽

Decision Trees ◽

Multilayer Perceptron ◽

Machine Learning Techniques ◽

Mobile Banking ◽

Classification Rules ◽

Learning Techniques ◽

Potential Customers

This paper profiles mobile banking users using machine learning techniques viz. Decision Tree, Logistic Regression, Multilayer Perceptron, and SVM to test a research model with fourteen independent variables and a dependent variable (adoption). A survey was conducted and the results were analysed using these techniques. Using Decision Trees the profile of the mobile banking adopter’s profile was identified. Comparing different machine learning techniques it was found that Decision Trees outperformed the Logistic Regression and Multilayer Perceptron and SVM. Out of all the techniques, Decision Tree is recommended for profiling studies because apart from obtaining high accurate results, it also yields ‘if–then’ classification rules. The classification rules provided here can be used to target potential customers to adopt mobile banking by offering them appropriate incentives.

Download Full-text

On Using Linear Diophantine Equations for Efficient Hiding of Decision Tree Rules

Proceedings of the 10th Hellenic Conference on Artificial Intelligence - SETN '18 ◽

10.1145/3200947.3201030 ◽

2018 ◽

Cited By ~ 3

Author(s):

Georgios Feretzakis ◽

Dimitris Kalles ◽

Vassilios S. Verykios

Keyword(s):

Decision Tree ◽

Diophantine Equations ◽

Linear Diophantine Equations

Download Full-text

Mate-tree: un algoritmo para la tarea de clasificación basado en operadores algebraicos y primitivas SQL [Mate-tree: an Algorithm for classification task based on algebraic operators and SQL primitives]

Ventana informatica ◽

10.30554/ventanainform.26.140.2012 ◽

2012 ◽

Author(s):

Ricardo Timarán Pereira

Keyword(s):

Data Mining ◽

Decision Tree ◽

Decision Trees ◽

Information Gain ◽

Classification Task ◽

Classification Algorithms ◽

Classification Rules ◽

Decision Tree Classification ◽

Expensive Process ◽

Algebraic Operators

Resumen La clasificación basada en árboles de decisión es el modelo más utilizado y popular por su simplicidad y facilidad para su entendimiento. El cálculo del valor de la métrica que permite seleccionar, en cada nodo, el atributo que tenga una mayor potencia para clasificar sobre el conjunto de valores del atributo clase, es el proceso más costoso del algoritmo utilizado. Para calcular esta métrica, no se necesitan los datos, sino las estadísticas acerca del número de registros en los cuales se combinan los atributos condición con el atributo clase. Entre los algoritmos de clasificación por árboles de decisión se cuentan ID-3, C4.5, SPRINT y SLIQ. Sin embargo, ninguno de estos algoritmos se basan en operadores algebraicos relacionales y se implementa con primitivas SQL. En este artículo se presenta Mate-tree, un algoritmo para la tarea de minería de datos clasificación basado en los operadores algebraicos relacionales Mate, Entro, Gain y Describe Classifier, implementados en la cláusula SQL Select con las primitivas SQL Mate by, Entro(), Gain() y Describe Classification Rules, los cuales facilitan el cálculo de Ganancia de Información, la construcción del árbol de decisión y el acoplamiento fuerte de este algoritmo con un SGBD. Palabras ClavesÁrboles de Decisión, Minería de Datos, Operadores Algebraicos Relacionales, Primitivas SQL, Tarea de Clasificación. Abstract Decision tree classification is the most used and popular model, because it is simple and easy to understand. The calculation of the value of the measure that allows selecting, in each node, the attribute with the highest power to classify on the set of values of the class attribute, is the most expensive process in the used algorithm. To compute this measure, the data are not needed, but the statistics about the number of records in which combine the test attributes with the class attribute. Among the classification algorithms by decision trees are ID-3, C4.5, SPRINT and SLIQ. However, none of these algorithms are based on relational algebraic operators and are implemented with SQL primitives. In this paper Mate-tree, an algorithm for the classification data mining task based on the relational algebraic operators Mate, Entro, Gain and Describe Classifier, is presented. They were implemented in the SQL Select clause with SQL primitives Mate by, Entro(), Gain() y Describe Classification Rules. They facilitate the calculation of the Information Gain, the construction of the decision tree and the tight coupled of this algorithm with a DBMS.KeywordsDecision Trees, Data Mining, Relational Algebraic Operators, SQL Primitives, Classification Task.

Download Full-text

Automated Development of Clinical Strategies Using Multistage Decision Analysis

Methods of Information in Medicine ◽

10.1055/s-0038-1635469 ◽

1986 ◽

Vol 25 (04) ◽

pp. 207-214 ◽

Cited By ~ 3

Author(s):

P. Glasziou

Keyword(s):

Decision Tree ◽

Decision Analysis ◽

Decision Trees ◽

Optimal Strategy ◽

Cholestatic Jaundice ◽

Clinical Strategies ◽

Simultaneous Study

SummaryThe development of investigative strategies by decision analysis has been achieved by explicitly drawing the decision tree, either by hand or on computer. This paper discusses the feasibility of automatically generating and analysing decision trees from a description of the investigations and the treatment problem. The investigation of cholestatic jaundice is used to illustrate the technique.Methods to decrease the number of calculations required are presented. It is shown that this method makes practical the simultaneous study of at least half a dozen investigations. However, some new problems arise due to the possible complexity of the resulting optimal strategy. If protocol errors and delays due to testing are considered, simpler strategies become desirable. Generation and assessment of these simpler strategies are discussed with examples.

Download Full-text

Performance Improvement of Decision Tree: A Robust Classifier Using Tabu Search Algorithm

Applied Sciences ◽

10.3390/app11156728 ◽

2021 ◽

Vol 11 (15) ◽

pp. 6728

Author(s):

Muhammad Asfand Hafeez ◽

Muhammad Rashid ◽

Hassan Tariq ◽

Zain Ul Abideen ◽

Saud S. Alotaibi ◽

...

Keyword(s):

Machine Learning ◽

Tabu Search ◽

Decision Tree ◽

Decision Trees ◽

Search Algorithm ◽

Learning Algorithms ◽

Performance Comparison ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Tabu Search Algorithm

Classification and regression are the major applications of machine learning algorithms which are widely used to solve problems in numerous domains of engineering and computer science. Different classifiers based on the optimization of the decision tree have been proposed, however, it is still evolving over time. This paper presents a novel and robust classifier based on a decision tree and tabu search algorithms, respectively. In the aim of improving performance, our proposed algorithm constructs multiple decision trees while employing a tabu search algorithm to consistently monitor the leaf and decision nodes in the corresponding decision trees. Additionally, the used tabu search algorithm is responsible to balance the entropy of the corresponding decision trees. For training the model, we used the clinical data of COVID-19 patients to predict whether a patient is suffering. The experimental results were obtained using our proposed classifier based on the built-in sci-kit learn library in Python. The extensive analysis for the performance comparison was presented using Big O and statistical analysis for conventional supervised machine learning algorithms. Moreover, the performance comparison to optimized state-of-the-art classifiers is also presented. The achieved accuracy of 98%, the required execution time of 55.6 ms and the area under receiver operating characteristic (AUROC) for proposed method of 0.95 reveals that the proposed classifier algorithm is convenient for large datasets.

Download Full-text

A Practical Tutorial for Decision Tree Induction

ACM Computing Surveys ◽

10.1145/3429739 ◽

2021 ◽

Vol 54 (1) ◽

pp. 1-38

Author(s):

Víctor Adrián Sosa Hernández ◽

Raúl Monroy ◽

Miguel Angel Medina-Pérez ◽

Octavio Loyola-González ◽

Francisco Herrera

Keyword(s):

Decision Tree ◽

Decision Trees ◽

Machine Learning Techniques ◽

Evaluation Measures ◽

Decision Tree Induction ◽

Learning Techniques ◽

Tree Models ◽

Evaluation Measure ◽

Main Components ◽

Support Decision Making

Experts from different domains have resorted to machine learning techniques to produce explainable models that support decision-making. Among existing techniques, decision trees have been useful in many application domains for classification. Decision trees can make decisions in a language that is closer to that of the experts. Many researchers have attempted to create better decision tree models by improving the components of the induction algorithm. One of the main components that have been studied and improved is the evaluation measure for candidate splits. In this article, we introduce a tutorial that explains decision tree induction. Then, we present an experimental framework to assess the performance of 21 evaluation measures that produce different C4.5 variants considering 110 databases, two performance measures, and 10× 10-fold cross-validation. Furthermore, we compare and rank the evaluation measures by using a Bayesian statistical analysis. From our experimental results, we present the first two performance rankings in the literature of C4.5 variants. Moreover, we organize the evaluation measures into two groups according to their performance. Finally, we introduce meta-models that automatically determine the group of evaluation measures to produce a C4.5 variant for a new database and some further opportunities for decision tree models.

Download Full-text

Evolutionary Algorithm for Improving Decision Tree with Global Discretization in Manufacturing

Sensors ◽

10.3390/s21082849 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2849

Author(s):

Sungbum Jun

Keyword(s):

Decision Tree ◽

Evolutionary Algorithm ◽

Decision Trees ◽

Manufacturing Systems ◽

Ensemble Methods ◽

Machine Learning Techniques ◽

Learning Techniques ◽

Industrial Internet ◽

Tree Models ◽

Real World Datasets

Due to the recent advance in the industrial Internet of Things (IoT) in manufacturing, the vast amount of data from sensors has triggered the need for leveraging such big data for fault detection. In particular, interpretable machine learning techniques, such as tree-based algorithms, have drawn attention to the need to implement reliable manufacturing systems, and identify the root causes of faults. However, despite the high interpretability of decision trees, tree-based models make a trade-off between accuracy and interpretability. In order to improve the tree’s performance while maintaining its interpretability, an evolutionary algorithm for discretization of multiple attributes, called Decision tree Improved by Multiple sPLits with Evolutionary algorithm for Discretization (DIMPLED), is proposed. The experimental results with two real-world datasets from sensors showed that the decision tree improved by DIMPLED outperformed the performances of single-decision-tree models (C4.5 and CART) that are widely used in practice, and it proved competitive compared to the ensemble methods, which have multiple decision trees. Even though the ensemble methods could produce slightly better performances, the proposed DIMPLED has a more interpretable structure, while maintaining an appropriate performance level.

Download Full-text