Understanding Consumer Loyalty Using Neural Network

Deliana, Yosini; Rum, Irlan Adiyatma

doi:10.17512/pjms.2017.16.2.05

Cited by 13 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a number of studies that use ANN to model consumer behaviour (Deliana & Rum, ; Stencl, Popelka, & Stastny, ). This model is the fitting model for general purposes and is proven capable in estimating any continuous function.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

How does perception on green environment across generations affect consumer behaviour? A neural network process

Deliana

Rum

2019

Int J Consumer Studies

Self Cite

View full text Add to dashboard Cite

This paper examines how the perception on green environment can affect consumer behaviour. It tests whether consumer behaviour responds to environmental change. This study captures the interaction between green environment perception and behaviour. A neural network analysis is used to address this challenge to model such a behaviour. A total of 462 interviews were conducted and analysed using neural network process. A Scaled Conjugate Gradient with random data division was used in training and the performance was calculated using mean square error. The result reveals that perception–behaviour gap exists across generations on green environment. It indicates that perception on green producing, green living, green transport and green product is an important factor in determining the behaviour on green consumption. The neural network accurately recognized green behaviour up to nearly 82% with MSE = 0.09 at epoch 31, which is a high level of recognition accuracy. This study underlines the existence of perception–behaviour gap on green environment. However, these are only identified to people with low‐to‐medium level of green behaviours (level of correct only 44.5% and 30%). People with high level of green behaviour in fact show consistency between their perceptions and behaviours (level of correct 96.4%). This result shows that people tend to have higher perceptions on green environment, but their behaviour reflects otherwise.

show abstract

Section: Methodsmentioning

confidence: 99%

“…There are a number of studies that use ANN to model consumer behaviour (Deliana & Rum, 2017;Stencl, Popelka, & Stastny, 2011).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

How does perception on green environment across generations affect consumer behaviour? A neural network process

Deliana

Rum

2019

Int J Consumer Studies

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, De Backer, DeStefano, Menon, and Suh [11] are optimistic that AI-related jobs might be injected into the market and which would be highly specialized and engineering-related tasks. De Stefano [2] also inferred that AI implementation, if not approached cautiously, might prompt or widen the income equality divide; with Frey and Osborne [20] affirming that this divide would be a predictor of unstable societies, with no country's economy an exception [36].…”

Section: Literature Reviewmentioning

confidence: 99%

Economic Impact of Artificial Intelligence: New Look for the Macroeconomic Assessment in Asia-Pacific Region

Haseeb¹,

Sasmoko²,

Mihardjo³

et al. 2019

IJCIS

View full text Add to dashboard Cite

To determine the impact of artificial intelligence (AI) on the selected economies in the Asia-Pacific region. Methods: This secondary research collected data from macroeconomic and AI-specific data sets. The sources of data from which insights were gained included digital technology sectors and corporations and their functions. The focus was on the need to assess the capability of AI on business operations The macroeconomic data was collected from data resources of international organizations' including the World Economic Forum, the Organization for Economic Cooperation and Development (OECD), the World Intellectual Property Organization (WIPO), and the International Telecommunication Union (ITU). In addition, this study has considered 19 economic indicators to analyze the economic outcome of AI in selected economies of Asia-Pacific. Results: From the results, the period between 2014 and 2016 witnessed China leading with over 25,000 citable documents on the AI topic. Regarding institutions that were observed to publish over 500 times on the AI topic, the countries in the ascending order include China (600), Hong Kong (1,100), and Singapore (2,000). As such, this study established that Asia-Pacific economies such as Hong Kong and Singapore though have smaller populations, but the majority of their higher education institutions have made a significant contribution to AI research; with the small economies also having a relatively higher number of computer scientists among the top 1,000 individuals. Additionally, through empirically analyses, during 1998-2016 with annual observations, it is found that various economic outcomes of AI were presented in 8 economies of targeted region. Limitations: At first, the future outlook of AI is just discussed in conceptual meaning while empirical context still needs to be examined in upcoming studies. At second, covering the overall South Asian region provides better findings with more generalization which is missing in current research. At third, other dimensions of AI and economy like implication of AI impact index and its relationship with macroeconomic variables is also missing in current research which could be reconsidered in coming studies. Conclusion: It is evident that AI exhibits the potential to be the main driver of Asia-Pacific's economic growth. Relative to the net and gross effect of AI on labor markets and the gross domestic product (GDP) of the top Asia-Pacific economies demonstrate that by 2030, AI might yield a 16-percent increase in output, translating into an estimated amount of $13 trillion. Overall, it is concluded that Asia-Pacific, when compared to developed regions such as North America, is lagging but the availability of a large pool of user data implies that the region can move ahead-given better resource and talent allocation.

show abstract

“…Indonesian people in general and East Java in particular have a habit of drinking coffee every day. Many circles with various kinds of social status favor coffee with a variety of consumption purposes, both for consumption of beverages in general, which are related to consumptive nature and changes in people's lifestyles [12][13][14] as well as for consumption related to health, among others, to prevent neurological diseases, reduce the risk of breast cancer, prevent diabetes, and efficacious revitalize new skin cells [15][16][17][18][19][20] Based on the type, processed coffee on the market has two types of brewed coffee and instant coffee. Each type of coffee has its own consumers [23].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Factors That Affect Consumer Preference on Coffee Consumption in Surabaya

Sudiyarto¹,

Destiarni²,

Harya³

2018

Proceedings of the International Conference on Science and Technology (ICST 2018)

View full text Add to dashboard Cite

There are two variants of processed coffee, there are brewed coffee and instant coffee. Each coffee have their own consumers. The difference of consumer preference on coffee consumption led to research idea about factors that affecting consumer preference on coffee consumption. This research was conducted to determine factors that affecting consumer preference on consuming between brewed coffee and instant coffee by the case study was taken in Surabaya. Factors that affecting preference of coffee selection are gender, age, last education, coffee drinking experience, early age of coffee consumption, and number of family members. With number of respondents equal to 57 respondents, this research would be analyzed by using logistic regression to determine the opportunity of which coffee were preferred by consumers. Based on parameter estimation result, four variables had a significant effect, there were gender, last education, drinking coffee experience, and number of family members. The four independent variables could explain the model of coffee consumer preference around 51 percent. Opportunities of adult male, with high school education level; drinking coffee experience around 11 -20 years; and number of families were more than five, consumed instant coffee around 0.13. Unlike the female consumer who preferred consuming instant coffee with opportunities was around 0.81 to brewed coffee. Producers have to be able to see that the calculation is an opportunity for them to differentiate their owned coffee product. Coffee producers can compete by making product innovation which could be affordable to all consumers both male and female.

show abstract

Understanding Consumer Loyalty Using Neural Network

Cited by 13 publications

References 17 publications

How does perception on green environment across generations affect consumer behaviour? A neural network process

How does perception on green environment across generations affect consumer behaviour? A neural network process

Economic Impact of Artificial Intelligence: New Look for the Macroeconomic Assessment in Asia-Pacific Region

Analysis of Factors That Affect Consumer Preference on Coffee Consumption in Surabaya

Contact Info

Product

Resources

About