The family economy is a critical indicator of the well-being of a family institution. It can be seen by the total income and how well the household finances is managed. In Malaysia, the household income level is categorized as B40, M40 and T20. These categories can also indicate the poverty level of the household. Overspending is a phenomenon where the monthly expenses are more than the household's total income, which affects economic wellbeing. Finding important factors that affect the spending patterns among the household can reveal the causes of overspending. It will assist the government in mitigating such problems. Availability of 4 million household expenditure records obtained from the survey conducted in 2016 by the Department of Statistics Malaysia eases the aim of this study to develop a household overspending model by using machine learning. The model is developed using 12 household demographic attributes with 14451 household records. The attributes are the number of households, area, state, strata, race, highest certificate, marital status, gender, housing, income, total expenditure, and category as attributes class. The model development employs five machine learning algorithms namely decision tree, Naïve Bayes, Neural network, Support Vector Machines, Nearest Neighbour. The results show that the decision tree through J48 algorithm has produced the easiest rule to be interpreted. The model shows four attributes which were income, state, races and number of households that highly influence the overspending problem. Based on the research finding, it can be concluded that these attributes are essential for improving the indicator measure for Malaysian Family Wellbeing Index in the aspect of overspending.

Nowadays, many people use Internet to do online activity. This scenario exposed them to danger in Internet which is phishing attack. In order to solve phishing attack, the anti-phishing solutions are needed. Based on our review, there are still lacks of articles that review on the types of anti-phishing solutions in detail. In this paper, a general idea of phishing attack and anti-phishing solutions is presented. The phishing attack can be classified into two categories which are social engineering and malware-based phishing attack. The anti-phishing solutions can be differentiating into two types which are phishing prevention and phishing detection. Compared to phishing prevention, the phishing detection is more important to solve the phishing attack. In phishing detection, there are two categories which are user awareness and software detection. The software detection has two methods which are traditional and automatic. There are two types for automatic method of software detection which are public phishing detection toolbars and academic phishing detection / classification schemes. Based on the comparison of all types of phishing detection, the academic phishing detection / classification schemes are more useful for phishing detection. For future work, we can do more research on the academic phishing detection / classification schemes that utilize deep learning to see its potential of accuracy to detect phishing websites.

No abstract

Requirement prioritization is a process in requirement engineering, which is a part of software development life cycle (SDLC). Requirement is prioritized due to constraints such as budget, time and resource allocation. Requirements of software is often classified as functional requirements (FR), and non-functional requirement (NFR). In order to produce a high-quality software, both requirement must be considered during requirement prioritization process. Various prioritization techniques have been invented, and Analytical Hierarchical Prioritization (AHP) is the most popular technique that has been cited. However, AHP does not support the NFR and unscalable. Meanwhile, Hierarchy-AHP has been introduced unto increase the scalability of AHP by using hierarchical requirements as input. Nevertheless, hierarchy-AHP does not meant for NFR and experimental result for increasing the scalability is not received significant attention. Thus, we intend to use NFR with large dataset on hierarchy-AHP. Aim of this paper is an exploration of hierarchy-AHP experimenting on RALIC dataset. Our major findings are: (i) NFR can be used hierarchy-AHP with minor process amendment, and (ii) hierarchy-AHP able to reduce pairwise comparison which is up to 97.33% for 403 number of requirements, compared to original AHP.

Nowadays, the number of web pages on the World Wide Web has been increasing due to the popularity of the Internet usage. The web page classification is needed in order to organize the increasing number of web pages. There are many web page classification techniques that have been proposed by the other researchers. However, there is no comprehensive survey on the performance of the techniques for the web page classification. In this paper, surveys of the different web page classification techniques with the result of the techniques achieved are presented. The existing works of web page classification are reviewed. Based on the survey, we found that the neural network technique namely Convolutional Neural Network (CNN) produce high F-measure value and meet the real-time requirement for classification compared to the other machine learning technique.