Prediction of robo-advisory acceptance in banking services using tree-based algorithms.

Area of Science:

• * Financial technology and artificial intelligence in banking.
• * Consumer behavior and adoption of digital services.

Background:

• * The banking sector is adopting robo-advisory services for increased efficiency and improved customer service.
• * Robo-advisory utilizes customer data from various communication channels.
• * Predicting consumer interest is crucial for effective promotional strategies.

Purpose of the Study:

• * To construct and evaluate predictive models for consumer acceptance of bank robo-advisory services.
• * To determine if existing bank data can identify customers interested in robo-advisory.
• * To enhance the effectiveness of marketing campaigns for digital banking solutions.

Main Methods:

• * Development of tree-based predictive models using machine learning algorithms (decision trees, ensemble models).
• * Utilized survey data on artificial intelligence in the Polish banking sector.
• * Predictors included socio-demographics, digital technology attitudes, banking experience, and trust in banks.

Main Results:

• * Constructed models effectively predict consumer acceptance of robo-advisory services.
• * Identified key factors influencing customer attitudes towards digital banking tools.
• * Demonstrated the utility of machine learning in understanding consumer adoption patterns.

Conclusions:

• * Predictive models can accurately forecast customer adoption of robo-advisory.
• * Leveraging customer data enhances targeted marketing for innovative banking services.
• * The study provides valuable insights for banks implementing AI-driven financial advisory.