Like/Dislike Prediction for Sport Shoes With Electroencephalography: An Application of Neuromarketing

Abstract

Neuromarketing is an emerging research field for prospective businesses on consumer’s preference. Consumer’s preference prediction based on electroencephalography (EEG) can reliably predict likes or dislikes of a product. However, the current EEG prediction and classification accuracy have yet to reach ideal level. In addition, it is still unclear how different brain region information and different features such as power spectral density, brain asymmetry, differential entropy, and Hjorth parameters affect the prediction accuracy. Our study shows that by taking footwear products as an example, the recognition accuracy of product likes or dislikes reaches 94.22%. Compared with other brain regions, the features of the frontal and occipital brain region obtained a higher prediction accuracy, but the fusion of the features of the whole brain region could improve the prediction accuracy of likes or dislikes even further. Future work would be done to correlate the EEG-based like or dislike prediction results with product sales and self-reports.

El estudio de las emociones en el contexto del neuromarketing: una aproximación práctica y conceptual

“…Cada una de dichas neuronas constituye un diminuto dipolo eléctrico, cuya polaridad depende de que el impulso a la célula sea inhibitorio o excitatorio (Ramos-Argüelles et al, 2009). Para poder recoger y registrar una señal de la actividad eléctrica en cada región cerebral a través de la superficie craneal se colocan electrodos que captan la diferencia de potencial entre ellos (Zeng et al, 2021). La EEG realiza el estudio y análisis de los campos eléctricos cerebrales (topografía, polaridad y su variación espacial temporal) mediante la amplificación de la diferencia de potencial entre los electrodos receptores de la señal.…”

A systematic review on EEG-based neuromarketing: recent trends and analyzing techniques

“…It is the most commonly used feature in Neuromarketing studies as presented in Table 4 . The asymmetry in EEG band power is an indicator of consumer preferences, which is why it is widely used in Neuromarketing [ 10 , 40 , 68 , 72 ]. To determine the power spectra of EEG sub-bands, firstly a Fast Fourier Transform (FFT) algorithm is used to calculate the Discrete Fourier Transform (DFT) of the EEG signal sequence as given by Eq.…”

“…Neuromarketing studies how people's brains react to particular ads, package designs, products, etc., using non-invasive brain-scanning techniques, such as EEG [ 8 – 10 ], functional magnetic resonance imaging (fMRI) [ 11 – 13 ], functional near-infrared spectroscopy (fNIRS) [ 14 , 15 ], etc. These neurophysiological data may now accurately represent customers' preferences, likes, and dislikes using modern feature extraction and classification algorithms [ 16 ].…”

Self-reported and electroencephalogram responses to evaluate sponsorship congruence efficacy.

“…Wang et al, 2022), and beta (Boksem & Smidts, 2015; Zeng et al, 2022) frequencies are also correlated with preference judgments. According to Zeng et al (2022), preference indices based on brain asymmetries, such as the approach-withdrawal index, valence, choice index, and effort index, are also used to predict consumer preferences (Aldayel et al, 2021). According to Boksem and Smidts (2015), this method allows marketers to obtain information that cannot be reliably obtained using traditional methods with a relatively small sample size with a true predictive ability of commercial success.…”

“…However, some research has also shown that gamma (Ramsøy et al, 2018), theta (A. Wang et al, 2022), and beta (Boksem & Smidts, 2015; Zeng et al, 2022) frequencies are also correlated with preference judgments. According to Zeng et al (2022), preference indices based on brain asymmetries, such as the approach-withdrawal index, valence, choice index, and effort index, are also used to predict consumer preferences (Aldayel et al, 2021).…”