M. Tahar Kechadi

Multi-objective feature selection by using NSGA-II for customer churn prediction in telecommunications

This paper proposes a new multiobjective feature selection approach for churn prediction in telecommunication service field, based on the optimisation approach NSGA-II. The basic idea of this approach is to modify the approach NSGA-II to select local feature subsets of various sizes, and then to use the method of searching nondominated solutions to select the global nondominated feature subsets. Finally, the method FBSM which yields the fitness thresholds is proposed to choose the global solutions with the lowest ranks as the final solutions. In order to evaluate the proposed approach, experiments were carried out and the experimental results show that the proposed feature selection approach is efficient for churn prediction with multiobjectives.

Cloud forensics definitions and critical criteria for cloud forensic capability: An overview of survey results

With the rapid growth of global cloud adoption in private and public sectors, cloud computing environments is becoming a new battlefield for cyber crime. In this paper, the researcher presents the results and analysis of a survey that was widely circulated among digital forensic experts and practitioners internationally on cloud forensics and critical criteria for cloud forensic capability in order to better understand the key fundamental issues of cloud forensics such as its definition, scope, challenges, opportunities as well as missing capabilities based on the 257 collected responses.

A new feature set with new window techniques for customer churn prediction in land-line telecommunications

In order to improve the prediction rates of churn prediction in land-line telecommunication service field, this paper proposes a new set of features with three new input window techniques. The new features are demographic profiles, account information, grant information, Henley segmentation, aggregated call-details, line information, service orders, bill and payment history. The basic idea of the three input window techniques is to make the position order of some monthly aggregated call-detail features from previous months in the combined feature set for testing be as the same one as for training phase. For evaluating these new features and window techniques, the two most common modelling techniques (decision trees and multilayer perceptron neural networks) and one of the most promising approaches (support vector machines) are selected as predictors. The experimental results show that the new features with the new window techniques are efficient for churn prediction in land-line telecommunication service fields.

An effective hybrid learning system for telecommunication churn prediction

Abstract Customer churn has emerged as a critical issue for Customer Relationship Management and customer retention in the telecommunications industry, thus churn prediction is necessary and valuable to retain the customers and reduce the losses. Moreover, high predictive accuracy and good interpretability of the results are two key measures of a classification model. More studies have shown that single model-based classification methods may not be good enough to achieve a satisfactory result. To obtain more accurate predictive results, we present a novel hybrid model-based learning system, which integrates the supervised and unsupervised techniques for predicting customer behaviour. The system combines a modified k-means clustering algorithm and a classic rule inductive technique (FOIL). Three sets of experiments were carried out on telecom datasets. One set of the experiments is for verifying that the weighted k-means clustering can lead to a better data partitioning results; the second set of experiments is for evaluating the classification results, and comparing it to other well-known modelling techniques; the last set of experiment compares the proposed hybrid-model system with several other recently proposed hybrid classification approaches. We also performed a comparative study on a set of benchmarks obtained from the UCI repository. All the results show that the hybrid model-based learning system is very promising and outperform the existing models.

Mathpad: A Fuzzy Logic-Based Recognition System for Handwritten Mathematics

Currently available methods for inputting mathematical expressions are counter-intuitive and require knowledge of keywords. In this paper we present a recognition system for handwritten mathematics, with the goal of enabling users to enter mathematics in the customary fashion. Our approach centres around the use of fuzzy logic, with fuzzy rules being used to extract features, classify symbols, and assess spatial relationships. Taking advantage of the fuzzy information available, our structural analysis algorithm weighs up which candidate symbol identities and spatial relationships are worth exploring, and maintains numerous possible expression trees. The most likely tree is ultimately chosen as the result. The system has achieved high recognition rates on a database of expressions written by multiple users.

Key Terms for Service Level Agreements to Support Cloud Forensics

As cloud adoption grows, the importance of preparing for forensic investigations in cloud environments also grows. A recent survey of digital forensic professionals identified that missing terms and conditions regarding forensic activities in service level agreements between cloud providers and cloud consumers is a significant challenge for cloud forensics. This paper addresses the challenge by specifying standard terms for service level agreements that support cloud forensics.

Customer Segmentation Architecture Based on Clustering Techniques

Knowledge on consumer habits is essential for companies to keep customers satisfied and to provide them personalised services. We present a data mining architecture based on clustering techniques to help experts to segment customer based on their purchase behaviours. In this architecture, diverse segmentation models are automatically generated and evaluated with multiple quality measures. Some of these models were selected for given quality scores. Finally, the segments are compared. This paper presents experimental results on a real-world data set of 10000 customers over 60 weeks for 6 products. These experiments show that the models identified are useful and that the exploration of these models to discover interesting trends is facilitated by the use of our architecture.

An ontology-based approach for the reconstruction and analysis of digital incidents timelines

Due to the democratisation of new technologies, computer forensics investigators have to deal with volumes of data which are becoming increasingly large and heterogeneous. Indeed, in a single machine, hundred of events occur per minute, produced and logged by the operating system and various software. Therefore, the identification of evidence, and more generally, the reconstruction of past events is a tedious and time-consuming task for the investigators. Our work aims at reconstructing and analysing automatically the events related to a digital incident, while respecting legal requirements. To tackle those three main problems (volume, heterogeneity and legal requirements), we identify seven necessary criteria that an efficient reconstruction tool must meet to address these challenges. This paper introduces an approach based on a three-layered ontology, called ORD2I, to represent any digital events. ORD2I is associated with a set of operators to analyse the resulting timeline and to ensure the reproducibility of the investigation.

Leveraging Decentralization to Extend the Digital Evidence Acquisition Window: Case Study on Bittorrent Sync

6th International Conference on Digital Forensics and Cyber Crime (ICDF2C 2014), New Haven, Connecticut, United States, 18-20 September 2014

A Tree-Based Approach for Detecting Redundant Business Rules in Very Large Financial Datasets

Net Asset Value NAV calculation and validation is the principle task of a fund administrator. If the NAV of a fund is calculated incorrectly then there is huge impact on the fund administrator; such as monetary compensation, reputational loss, or loss of business. In general, these companies use the same methodology to calculate the NAV of a fund; however the type of fund in question dictates the set of business rules used to validate this. Today, most Fund Administrators depend heavily on human resources due to the lack of an automated standardized solutions, however due to economic climate and the need for efficiency and costs reduction many banks are now looking for an automated solution with minimal human interaction; i.e., straight through processing STP. Within the scope of a collaboration project that focuses on building an optimal solution for NAV validation, the authors will present a new approach for detecting correlated business rules and show how they evaluate this approach using real-world financial data.