Predicting the relationship between consumer buying behavior (CBB) and consumption metaphor (CM) through machine learning (ML)

Koyluoglu, Alaaddin Selcuk; Esme, Engin

Predicting the relationship between consumer buying behavior (CBB) and consumption metaphor (CM) through machine learning (ML)

Management & Marketing

Volume 20 (2025): Issue 1 (March 2025)

By: Alaaddin Selcuk Koyluoglu and Engin Esme

Open Access

|Mar 2025

Figures & Tables

Cronbach’s alpha test_

Scale	Number of expression	Cronbach alpha
CM	4	0.823
CBB	11	0.792

Prediction with metaphor variables by using NCFS_

Method	Accuracy	Specificity	Precision	Recall	F-Measure
KNN	72.86	83.56	79.78	62.88	69.25
SVM	70.06	69.75	70.00	70.92	69.60
ELM	78.33	79.51	79.34	77.55	78.12

The algorithm steps of kNN_

1	Determine the value of k k ,
2	Calculate the distance between the new instance ( x ) \left(x) and the entire training set d ( x , y ) d(x\left,y) ,
3	Determine the k k nearest neighbors by sorting the distances from smallest to largest,
4	Determine the class of the new instance by majority voting.

Prediction with selected features by using NCFS_

Method*	Accuracy	Specificity	Precision	Recall	F-Measure
KNN	91.02	90.98	91.91	90.51	91.03
SVM	87.63	87.14	88.46	86.91	87.47
ELM	88.54	84.98	87.29	91.34	89.13

Distribution table of socio-demographic characteristics of the subjects participating in the study_

Variables		Frequency (f)	Percent (%)
Relationship (partner)	Yes	132	34.9
Relationship (partner)	No	246	65.1
Place of birth	Big city	171	45.2
	Province	99	26.2
	County	99	26.2
	Village	9	2.4
Living place	Big city	243	64.3
	Province	79	20.9
	County	46	12.2
	Village	10	2.6
Mother’s education level	Illiterate	23	6.1
	Primary school	156	41.3
	Secondary education	156	41.3
	University	43	11.4
Father’s education level	Illiterate	8	2.1
	Primary school	137	36.2
	Secondary education	162	42.9
	University	71	18.8
State of illness	Yes	48	12.7
State of illness	No	330	87.3
Total		378	100

Sample distribution table of the subjects participating in the study_

Variables		Frequency (f)	Percent (%)
Gender	Female	180	47.6
Gender	Male	198	52.4
Age	17–18	16	4.2
	19–20	177	46.8
	21–22	137	36.2
	23–24	33	8.7
	25 and more	15	4.0
Body type	Slim	92	24.3
	Normal	237	62.7
	Large	49	13.0
Educational level	Associate degree	299	79.1
Educational level	Bachelor’s degree	79	20.9
Science field	Social sciences	324	85.7
	Science	36	9.5
	Health Sciences	18	4.8
Level of income	1,000 TL and less	224	59.3
	2,000 TL	85	22.5
	3,000 TL	24	6.3
	4,000 TL	11	2.9
	5,000 TL and more	34	9.0
Total		378	100

Chi-Square analysis results among CBB categories_

			Would you like to get a tattoo?
			Yes	No	Total
Did you get a tattoo?	Yes, I did	Frequency	213	8	221
		Did you get a tattoo?	96.4%	3.6%	100.0%
		Would you like to get a tattoo?	29.3%	1.3%	16.5%
	No, I did not	Frequency	514	604	1,118
		Did you get a tattoo?	46.0%	54.0%	100.0%
		Would you like to get a tattoo?	70.7%	98.7%	83.5%
Total		Frequency	727	612	1,339
		Did you get a tattoo?	54.3%	45.7%	100.0%
		Would you like to get a tattoo?	100.0%	100.0%	100.0%

Kmo–Bartlett’s test_

Kaiser–Meyer–Olkin measure of sampling adequacy		0.835
Bartlett’s test of sphericity	Approx. chi-square	5174.812
	df	435
	Sig.	0.000

Goodness of fit indexes of scales_

Scale model	ΔX ²	sd	p	ΔX ²/sd	GFI	CFI	RMSEA	RMR
CM	7.274	6	0.06	1.21	0.85	0.97	0.03	0.04
CBB	5.489	3	.23	1.83	0.89	0.95	0.04	0.02

Model fit criteria goodness of fit index reference ranges_

Model fit criteria	Good fit	Acceptable fit
X ² Uyum Testi	0.05 < p ≤ 1	0.01 < p ≤ 0.05
CMIN/SD	X ²/sd ≤ 3	X ²/sd ≤ 5
	Comparative fit indexes
CFI	0.97 ≤ CFI	0.95 ≤ CFI
RMSEA	RMSEA ≤ 0.05	RMSEA ≤ 0.08
	Absolute fit indexes
GFI	0.90 ≤ GFI	0.85 ≤ GFI
	Residual compliance indexes
RMR	0 < RMR ≤ 0.05	0 < RMR ≤ 0.08

Correlation analysis results_

Measurement data	1	2
1. CM	1
2. CBB	0.315**	1

The algorithm steps of ELMs_

1	Assign weights w i {w}_{i} and biases b i {b}_{i} randomly
2	Calculate hidden layer output, H
3	Calculate output weight matrix , β ˆ = H † · T \hat{\beta }={H}^{\dagger }{\rm{\cdot }}T
4	Use T = H β ˆ T=H\hat{\beta } to predict the classes of testing data

NCA feature selection_

1	Procedure NCFS ( T , α , σ , λ , η ) {\rm{NCFS}}(T,\alpha ,\sigma ,\lambda \left,\eta ) : T: training set, α \alpha : initial step length, σ \sigma : kernel width, λ \lambda : regularization parameter, η \eta : small positive constant;
2	Initialization: w ( 0 ) = ( 1 , 1 , … , 1 ) , ϵ ( 0 ) = − ∞ , t = 0 {w}^{\left(0)}=(1,1,\ldots ,\hspace{1em}1),{\epsilon }^{\left(0)}=-{\rm{\infty }},t=0
3	repeat
4	for I = 1, …, N do
5	Compute p ij {p}_{{ij}} and p i {p}_{i} using w ( t ) {w}^{\left(t)} according to (2) and (3)
6	for l = 1, …, d do
7	∆ l = 2 1 σ ∑ i p i ∑ j ≠ i p ij \| x il − x jl \| − ∑ j y ij p ij \| x il − x jl \| − λ w l ( t ) {\triangle }_{l}=2\left(\phantom{\rule[-0.75em]{}{0ex}},\frac{1}{\sigma }{\sum }_{i}\left(\phantom{\rule[-0.75em]{}{0ex}}{p}_{i}{\sum }_{j\ne i}{p}_{{ij}}\|{x}_{{il}}-{x}_{{jl}}\|-{\sum }_{j}{y}_{{ij}}{p}_{{ij}}\|{x}_{{il}}-{x}_{{jl}}\|\right)-\lambda \right){w}_{l}^{(t)}
8	t = t + 1 t=t+1
9	w l ( t ) = w l ( t − 1 ) {w}_{l}^{\left(t)}={w}_{l}^{(t-1)}
10	ϵ ( t ) = ε ( w ( t − 1 ) ) {\epsilon }^{\left(t)}=\varepsilon ({w}^{(t\left-1)})
11	if ϵ ( t ) > ϵ ( t − 1 ) {\epsilon }^{\left(t)}\gt {\epsilon }^{(t\left-1)} then
12	α = 1.01 α \alpha =1.01\alpha
13	else
14	α = 0.4 α \alpha =0.4\alpha
15	until \| ϵ ( t ) − ϵ ( t − 1 ) \| < η \|{\epsilon }^{\left(t)}-{\epsilon }^{(t\left-1)}\|\lt \eta
16	w = w ( t ) w={w}^{\left(t)}
17	return w w

Prediction with all features_

Method*	Accuracy	Specificity	Precision	Recall	F-Measure
KNN	89.77	87.33	89.26	91.64	90.27
SVM	87.54	85.46	87.49	88.72	87.84
ELM	87.32	81.48	85.49	91.60	88.23

Exploratory factor analysis_

		Factor 1	Factor 2
CM Cr. Alpha = 0.823	Get experience with tattooing	0.618
	Desire to join a community	0.847
	Socialization or group interaction	0.902
	Social differentiation	0.846
CBB Cr. alpha = 0.792	Do you have a tattoo?		0.441
	Would you like to get a tattoo?		0.701
	What are the reasons why you don’t want to get a tattoo?		0.650
	Do you want to get a permanent tattoo or a temporary tattoo?		0.897
	On which part(s) of your body did you have your tattoo done or would you like to have it done?		0.599
	Does anyone in your family have a tattoo?		0.850
	Do any of your friends have tattoos?		0.875

DOI: https://doi.org/10.2478/mmcks-2025-0001 | Journal eISSN: 2069-8887 | Journal ISSN: 1842-0206

Journal RSS Feed

Language: English

Page range: 35 - 51

Submitted on: Aug 15, 2024

Accepted on: Jan 23, 2025

Published on: Mar 30, 2025

Published by: Society for Business Excellence

In partnership with: Paradigm Publishing Services

Publication frequency: 4 issues per year

Keywords:

Consumer buying behavior,

Consumption metaphor,

Artificial intelligence,

Machine learning

Related subjects:

Business and economics,

Business management,

Marketing, sales, customer relations,

Management, organization, corporate governance,

Business development, change management, cooperation,

Entrepreneurship

© 2025 Alaaddin Selcuk Koyluoglu, Engin Esme, published by Society for Business Excellence
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous article Volume 20 (2025): Issue 1 (March 2025)Next article

Predicting the relationship between consumer buying behavior (CBB) and consumption metaphor (CM) through machine learning (ML)

Figures & Tables

Figure 1

Figure 2

Figure 3

Figure 4

Cronbach’s alpha test_

Prediction with metaphor variables by using NCFS_

The algorithm steps of kNN_

Prediction with selected features by using NCFS_

Distribution table of socio-demographic characteristics of the subjects participating in the study_

Sample distribution table of the subjects participating in the study_

Chi-Square analysis results among CBB categories_

Kmo–Bartlett’s test_

Goodness of fit indexes of scales_

Model fit criteria goodness of fit index reference ranges_

Correlation analysis results_

The algorithm steps of ELMs_

NCA feature selection_

Prediction with all features_

Exploratory factor analysis_

Paradigm

My account