9143 research outputs found
Sort by
Development of customer response prediction model for personal loan using logistic regression
Get PDFIn general, financial service companies use mass media marketing strategies to offer and promote a product or service to their customers. This strategy is seen as less effective because differences in customer interests are not taken into account. With a large customer database, financial service companies have shifted from unproductive mass media marketing strategies to targeted marketing strategies by identifying customers who are likely to respond to more specific products and services. However, this strategy appears challenging when implemented manually through a large customer database. Therefore,
data mining techniques are used to develop accurate customer response forecasting
models. The goal of this study is to develop a customer response model to predict whether
a customer will respond to a personal loan product using logistic regression and decision
tree techniques. For modelling purposes, 10,952 customer data were collected from one
commercial bank in Malaysia. Factor analysis was conducted to identify inputs for the
model. Finally, logistic regression and decision tree techniques were used to develop the
customer response model. Different models from these two techniques were compared.
The best model for predicting customers who are likely to respond to personal loan
products was selected based on the highest accuracy, precision, and recall values. Both
models had the same accuracy of around 98%. However, decision tree performed slightly
better than regression, especially for 10-fold cross-validation. For 5-fold cross-validation,
logistic regression performed well. In most cases, decision trees should perform better in
business scenarios where logistic regression performs better when data contamination is
low. This study can benefit banks by maximizing customer response to product offers,
minimizing overall market costs, and improving customer relationship managemen
The effect of consumer's need for uniqueness and emotional experience on brand pride: The mediating role of electronic word-of-mouth
Get PDFBrand pride generates positive emotions and increases brand loyalty, leading to more word-of- mouth advertising. It is necessary to emphasize the need to raise awareness of national cosmetics and promote beauty through simplicity and originality. This study investigates the effect of consumer’s need for uniqueness and emotional experience on brand pride with the mediating role of eWOM. Primary data was collected from 394 Pakistani millennials and analyzed using partial least squares structural equation modeling via Smart PLS 3.0. The findings indicate that consumers’ need for uniqueness and emotional experiences significantly influenced eWOM. In addition, eWOM had a positive impact on the mediation between the consumer need for uniqueness, emotional experience and brand pride. This study broadens the scope of WOM research in the digital age and sheds light on diverse customer interactions. It also uncovers the growing trend of organic cosmetics due to increased awareness of cruelty-free products and offers insights into men's cosmetic preferences. The proposed research framework integrates the theory of uniqueness and the theory of brand congruence to advance knowledge about consumer need for uniqueness, emotional experiences and the impact of eWOM on Pakistani millennials' brand pride. The results highlight the importance of eWOM in shaping consumer decisions and make the case for further industry research. The findings have significant implications for marketers and platform administrators in managing consumer responses. Categorizing viewpoints resolves conflicts while customizing beauty perceptions and pricing strategies to target specific groups. The research also provides guidance to platform operators on improving usability and encouraging reviews
The augmented reality educational tool for learning 2D and 3D space content in primary school
Get PDFSpace is a Mathematics topic for the second level in Kurikulum Standard Sekolah Rendah (KSSR) syllabus that is difficult for primary school pupils to understand because it requires them to visualize the 3-dimensional shapes and 2-dimensional polygons in solving Mathematical questions. Therefore, Augmented Reality (AR) is
proposed due to its potential as it allows pupils to visualize the 3-dimensional and 2- dimensional shapes practically. The objective of this research is to develop an effective AR educational tool based on User Experience (UX) and the identified needs for primary school pupils to visualize 2-dimensional and 3-dimensional shapes in learning
Mathematics on Space topic. ASSURE instructional design model and quantitative approach have been used in this research. The quantitative approach focused on analysing users⁵ needs for the AR educational tool that has been developed and analysing its effectiveness. It involved surweys on the users' needs and the
effectiveness of the AR educational tool. This AR educational tool was developed following Waterfall Methodology and its effectiveness was evaluated using ISO/IEC 25022. All data were analysed to find the mean and were used to determine the users' needs for the development of the AR educational tool. The findings of the research
include a list of user needs, a successfully developed AR educational tool based on the UX, and users' needs obtained. The high mean of effectiveness test shows that the users were satisfied with the AR educational tool that had been developed. This research is very important as an effort to increase pupils9 understanding of space topic
and assist primary school teachers to implement teaching sessions more effectively
Factors influencing Malaysian consumers’ intention to purchase electric vehicles
Get PDFThe transition from petrol to electric vehicles (EVs) is a challenge for emerging markets in Malaysia. According to data from the Malaysian Automobile Association (MAA), Malaysian electric vehicle sales in 2022 will be only 2,631 units. By comparison, total vehicle sales nationwide are about 720,000 units. Research related to purchase intention of electric vehicles in Malaysia is still limited. At the same time, there is also a lack of research focusing on attitude as a moderating variable. Hence, the research objective of this paper is to identify the factors that influence Malaysian
consumers’ intention to purchase electric vehicles. In order to achieve these goals, this study established a research framework based on the Technology Acceptance Model (TAM), adopted quantitative research methods, conducted a questionnaire survey, and randomly selected 102 participants in Malaysia as a sample to understand the factors that influence consumers' intention to purchase electric vehicles. In this study, survey data were analyzed using IBM SPSS. The analysis results show that both perceived
ease of use and perceived usefulness have a positive impact on consumers' intention to purchase electric vehicles. This study also found that consumers' attitudes towards electric vehicles can play a moderating effect in the relationship between perceived
usefulness and purchase intention, and between perceived ease of use and purchase intention. According to our survey results, it is necessary to speed up the popularization of electric vehicle knowledge so that more consumers can develop a positive attitude
towards electric vehicles, thus changing their perceived usefulness of electric vehicles and thereby increasing their purchase intention. This study, fills the research gap on the moderating effect of consumers’ attitude towards EV. Furthermore, the results of this
study can serve as a basis for policy makers to formulate appropriate policies and provide guidance to EV companies targeting Malaysian consumers. For future research
in this area, it is suggested that the sample size collected could be expanded to be as representative of the entire Malaysian EV market as possible and keep questionnaire questions up to date with technological trend
Optimization of medical image steganography using n-decomposition genetic algorithm
Get PDFProtecting patients' confidential information is a critical concern in medical image steganography. The Least Significant Bits (LSB) technique has been widely used for secure communication. However, it is susceptible to imperceptibility and security risks due to the direct manipulation of pixels, and ASCII patterns present limitations. Consequently, sensitive medical information is subject to loss or alteration. Despite attempts to optimize LSB, these issues persist due to (1) the formulation of the optimization suffering from non-valid implicit constraints, causing inflexibility in reaching optimal embedding, (2) lacking convergence in the searching process, where the message length significantly affects the size of the solution space, and (3) issues of application customizability where different data require more flexibility in controlling the embedding process. To overcome these limitations, this study proposes a technique known as an n-decomposition genetic algorithm. This algorithm uses a variable-length search to identify the best location to embed the secret message by incorporating constraints to avoid local minimum traps. The methodology consists of five main phases: (1) initial investigation, (2) formulating an embedding scheme, (3) constructing a decomposition scheme, (4) integrating the schemes' design into the proposed technique, and (5) evaluating the proposed technique's performance based on parameters using medical datasets from kaggle.com. The proposed technique showed resistance to statistical analysis evaluated using Reversible Statistical (RS) analysis and histogram. It also demonstrated its superiority in imperceptibility and security measured by MSE and PSNR to Chest and Retina datasets (0.0557, 0.0550) and (60.6696, 60.7287), respectively. Still, compared to the results obtained by the proposed technique, the benchmark outperforms the Brain dataset due to the homogeneous nature of the images and the extensive black background. This research has contributed to genetic-based decomposition in medical image steganography and provides a technique that offers improved security without compromising efficiency and convergence. However, further validation is required to determine its effectiveness in real-world applications
Intellectual capital efficiency, ownership structure and firm performance: The moderating role of the board of directors
No full textSeveral studies on the effect of intellectual capital (IC) and ownership structure on firm performance had been conducted. However, their results in emerging nations such as Malaysia had remained uncertain and ambiguous due to inconclusive findings. Thus, this study examined the effect of IC and ownership structure (family, government and foreign ownership) on firm performance. The modified value-added intellectual coefficient (M-VAIC) model was utilized to measure IC efficiency inclusive of two new components (relational and innovation). In addition, this study also examined the composite measure of the board of directors' effectiveness as a moderator in the associations between IC, ownership structure and firm performance. This study employed a balanced panel data of 409 non-financial firms (2,045 firm-year observations) from 11 sectors listed on the Main Market of Bursa Malaysia over the period of five years (2016-2020). This study used the generalized method of the moment (GMM) to address the issues of endogeneity, autocorrelation and heteroscedasticity. The empirical findings revealed that IC efficiency was significant and positively associated to the performance of the Malaysian non-financial firms. Additionally, this study found that the ownership structure played a crucial role in improving the value and enhancing performance for Malaysian non-financial firms. Moreover, the board of directors' effectiveness significantly moderated the association between IC efficiency and ownership structure with firm performance. The results of this study could help managers in building new and innovative methods to get ahead competitively among non-financial firms by using the IC as a premise. The results would also be useful for directors and managers in developing new policies that will improve the corporate governance mechanisms, particularly on the ownership structure and board of directors' effectiveness
Work environment, reward and employee performance in banking sector: The mediating role of job satisfaction
Get PDFThis study focuses on the effects of work environment and reward on employee’s performance in the banking sector in Penang. The research framework consists of employee performance as the dependent variable and two factors were examined as the independent variables namely, work environment and reward. In addition, job satisfaction is included as the mediator. A total of 300 questionnaires were distributed to the banks and only 280 were responded. Data collected were analysed by using Statistical Package for Social Sciences (SPSS) version 26. Statistical techniques such as regression analysis, correlation analysis, descriptive analysis and reliability analysis were used. The findings revealed that work environment, reward and job satisfaction were positively correlated to employee performance. Moreover, job satisfaction also mediates the relationship between work environment, reward and employee performance. Further, few implications and recommendations are suggested in this study
The effect of service marketing mix on hotel preference by consumer
Get PDFFor the pass few years since Covid 19 strike world globe the hotel occupancy and demand had reduce drastically. The purchasing behaviors seem to change due the pandemic and indirectly change the consumer preferences. Therefore, this research aims to determine the relationship between service marketing mix and consumer hotel preference. This study also aims to analyze the influence of service marketing mix on consumer hotel preference in this study, the 7 pillars of the service marketing mix were used to better understand preferences in the hotel service industry: product, price, promotion, place, process, physical evidence, and people. The quantitative research method via Google form questionnaire was used as the research instrument to collect data. A total of 421 respondents were selected randomly using the convenience sampling technique. Descriptive analysis, multiple regression analysis, and correlation analysis were used to analyses the data in order to achieve the objective and conduct the research. The results of the study show a positive relationship between all the dependent variables and hotel preferences. The results indicated that the services marketing mix has a coefficient of determination of 32.6%, which indicates that the services marketing mix has an influence on the customer's hotel preference. Based on the results, we conclude that physical evidence and product effects affect hotel preference. This study helps to provide recommendations based on the findings of the research in order to enhance product quality and raise the standard of physical evidence in order to increase the hotel's influence on consumer preferences and use of its facilities. Although the impact of the other factors on the hotel's preferences is minimal, they must be maintained and enhanced to optimize its performance
Evaluation model of Educational Music Video for Children’s Learning (EMV4CL)
No full textVideo-based learning (VBL) has proven the benefits for teaching and learning process. Music video is one of VBL and highly potential as a learning support media due to its appealing content, especially for children’s learning. This study emphasizes the Educational Music Video (EMV), which is an adaption of the music video concept which presents content through singing narration. However, characteristics of VBL that focus on children's learning are still lacking, hence resulting in limited concern for enjoyable learning. Additionally, there is no specific guide for teachers to evaluate the content appropriateness of EMV for children’s learning. This study proposes an Evaluation Model of Educational Music Video for Children’s Learning (EMV4CL) emphasizing the components and elements of EMV to evaluate and select video appropriate for children’s learning. Therefore, four objectives are formulated and implemented using Design Research methodology to accomplish the research aim. The Evaluation Model of EMV4CL consists of five main components: video content, audio-visual learning concept, video presentation style, edutainment feature, and activity. 11 academic experts validated the model and mutually agreed that the model is well-developed as intended. Then, evaluation testing was conducted with primary school teachers to investigate the usefulness of the model using the Checklist Scale of EMV4CL (CSEMV4CL), which is a translated version of the model which consists of 75 items categorized into six dimensions. The testing results indicated that the CSEMV4CL is useful in facilitating the teachers to select and evaluate EMV appropriate for children’s learning. The main findings of this study are the Evaluation Model of EMV4CL and the CSEMV4CL which could be utilized as a tool in determining the appropriate content of EMV for children’s learning. The results of this study can improve existing knowledge in EMV for children's learning. The proposed model and checklist scale could serve as a guideline for teachers and developers to evaluate and produce quality EMV
The influence of digital literacy and digital technology acceptance on digital amnesia behaviour among digital natives
Get PDFPeople's lives are being transformed by increasing use of the Internet, which affects not only the way they work, but also the way they learn, behave, store and remember information.In the business world, this phenomenon is considered normal and nonharmful. However, a few research have studied the phenomenon, especially with regard to digital natives' behavior and perceptions. Therefore, this study is aimed to examine the influence of digital literacy self-efficacy and technology acceptance on digital amnesia behaviour of digital natives. Three studies have been conducted at Universitas Islam Negeri Ar-Raniry Banda Aceh, Indonesia.The first study used a descriptive quantitative approach by a survey method to identify nomophobia, Google effect, and digital amnesia among 110 students. The second study used a true experimental design with a post-test-only control group to investigate the effect of the phenomenon on memory retention and knowledge construction involving 40 students. The third study, an inferential quantitative approach with survey method was conducted among 375 students to examine the influence of digital literacy self-efficacy and digital technology acceptance on digital amnesia. In the first study, a Google form survey was used, while in the second study, 20 easy questions and a 5- minute video clip were used. The Structural Equation Modeling approach was applied in the third study and the sample size recommendation in PLS-SEM for a statistical power of 80% by Cohen (1992) was used as a sampling procedure. The first study revealed 83.9% of students experience Internet dependency, with 72% perceiving the phenomenon as normal. The second study revealed nomophobia, Google effect, and digital amnesia behaviour weakened memory retention and knowledge construction.In the third study, digital literacy self-efficacy and digital technology acceptance were found to negatively influence digital amnesia behaviour. These studies offer new insights into how digital technology can be used in the social sciences and educational fields efficiently, effectively, and positively