Beyond One-Size-Fits-All: A Study of Neural and Behavioural Variability Across Different Recommendation Categories

2025-06-16

AI Summary

Conventional recommender systems overemphasize accuracy and relevance while neglecting how distinct recommendation types—precise, substitute, complementary, and irrelevant—differentially impact user experience. Method: This work pioneers the integration of EEG neurophysiological signals with multidimensional behavioral logs in e-commerce to systematically decode category-specific neural–behavioral response variations across these four recommendation types. We employ ERP component analysis (e.g., P300 amplitude), cross-category statistical inference, and individual-difference modeling. Results: Recommendation type significantly modulates both neural activation (e.g., P300 amplitude differences, *p* < 0.001) and behavioral responses (click-through rate, dwell time), enabling an interpretable “category–response” mapping. Inter-individual variability in neural–behavioral responses reaches 37–52%, challenging purely algorithmic evaluation paradigms. Our findings establish a novel methodology and empirical foundation for neuroscience-informed recommendation optimization.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Traditionally, Recommender Systems (RS) have primarily measured performance based on the accuracy and relevance of their recommendations. However, this algorithmic-centric approach overlooks how different types of recommendations impact user engagement and shape the overall quality of experience. In this paper, we shift the focus to the user and address for the first time the challenge of decoding the neural and behavioural variability across distinct recommendation categories, considering more than just relevance. Specifically, we conducted a controlled study using a comprehensive e-commerce dataset containing various recommendation types, and collected Electroencephalography and behavioural data. We analysed both neural and behavioural responses to recommendations that were categorised as Exact, Substitute, Complement, or Irrelevant products within search query results. Our findings offer novel insights into user preferences and decision-making processes, revealing meaningful relationships between behavioural and neural patterns for each category, but also indicate inter-subject variability.

Problem

• Decoding neural and behavioral variability across recommendation categories
• Exploring user engagement beyond algorithmic relevance in Recommender Systems
• Analyzing EEG and behavioral responses to diverse e-commerce recommendations

Innovation

• Analyzed neural and behavioural responses to recommendations
• Used Electroencephalography and e-commerce dataset
• Categorized recommendations as Exact, Substitute, Complement, Irrelevant