Machine Learning-Based Analysis of Technology Acceptance in FinTech: A Behavioral Study Using Digital Wallet Data

Abstract The rapid growth of FinTech services, particularly robo-advisors, has transformed how individuals engage with digital financial platforms. Understanding the behavioral drivers of technology acceptance in this context is critical for enhancing adoption and designing more effective user experiences. This study investigates whether user-level behavioral and transactional data can be leveraged to predict technology acceptance, operationalized through daily app usage. Grounded in the Technology Acceptance Model (TAM) and Unified Theory of Acceptance and Use of Technology (UTAUT), the study uses behavioral proxies such as customer satisfaction, loyalty points, and lifetime value to reflect constructs like perceived usefulness, performance expectancy, and facilitating conditions. Using a real-world dataset of 7000 FinTech users sourced from Kaggle, we applied four machine learning algorithms, Logistic Regression, Support Vector Machine, Random Forest, and XGBoost, to classify users into high and low acceptance categories. Results revealed that ensemble models, particularly XGBoost, outperformed linear classifiers, achieving moderate improvements in precision and recall for the high-acceptance class. However, overall predictive performance remained constrained by class imbalance and overlapping behavioral patterns. These findings suggest that while machine learning can reveal patterns linked to technology acceptance, predictive precision remains limited without richer temporal and psychographic features. The study contributes to the evolving discourse on FinTech adoption by offering a data-driven lens to complement intention-based models and inform adaptive engagement strategies.