Skip to content

Identifying Consumer Ad Preferences: Utilizing Machine Learning for Exploratory Data Analysis and Feature Engineering with Neurophysiological Metrics

Advertising Analysis Reveals Predicting Consumer Ad Preferences Based on Detection of Seven Basic Emotions, Attention, and Engagement Stimulated by Advertisements

Examining Consumer Ad Preference Prediction: Utilizing Machine Learning Techniques for Exploratory...
Examining Consumer Ad Preference Prediction: Utilizing Machine Learning Techniques for Exploratory Data Analysis and Feature Engineering of Neurophysiological Indicators

Identifying Consumer Ad Preferences: Utilizing Machine Learning for Exploratory Data Analysis and Feature Engineering with Neurophysiological Metrics

In a recent research study, an artificial intelligence (AI) system was developed based on machine learning techniques. This AI system employs the k-Nearest Neighbors, Support Vector Machine, and Random Forest (RF) techniques to analyze consumer preferences.

The study, conducted by an unspecified research group at KIT ITAS, focuses on Facial Expression Analysis (FEA) and electrodermal activity (EDA) to predict consumer ad preferences beyond the initial mention. The Random Forest technique, in particular, demonstrated impressive results, achieving an 81% Accuracy, 84% Precision, 79% Recall, and an F1-score of 81% in predicting consumer preferences.

A significant aspect of this research is the integration of an eXplainable AI module. This module, based on feature importance, identifies Attention, Engagement, Joy, and Disgust as the most influential features in influencing consumer ad preference predictions.

The findings of this research suggest that these computerized intelligent systems can be effectively used as supporting tools for marketing specialists. By understanding the key emotional and behavioural factors that influence consumer preferences, marketing professionals can make more informed decisions and tailor their strategies accordingly.

This research does not provide new information about the statistical module integrated for inferential and exploratory analysis. However, it is clear that this module plays a crucial role in ensuring the validity and reliability of the AI system's predictions.

In conclusion, this research presents an innovative AI system that leverages Facial Expression Analysis and electrodermal activity to predict consumer ad preferences with impressive accuracy. The eXplainable AI module further enhances the system's utility by providing insights into the most influential features driving consumer preferences. These findings have the potential to revolutionise the field of marketing by enabling more personalised and effective advertising strategies.

Read also: