Uncovering Underlying Determinants of Bank Revenue
(2024) DABN01 20241Department of Statistics
Department of Economics
- Abstract (Swedish)
- For banks to remain resilient in times of economic instability, and what the Chair of the Supervisory Board of the European Central Bank refers to as; “radical uncertainty”, it is essential for banks to plan for the future. Challenges such as rising interest rates, climate change and geopolitical conflicts require proactive measures. Thus, accurately predicting bank revenue plays a crucial role in aiding banks in determining which strategies to implement and at what scale. Hence, this paper examines what bank-specific determinants influence revenue forecasting and prediction across different customer segments in Sweden using machine learning algorithms such as XGBoost and Random forest. Additionally, it analyses whether there are distinct... (More)
- For banks to remain resilient in times of economic instability, and what the Chair of the Supervisory Board of the European Central Bank refers to as; “radical uncertainty”, it is essential for banks to plan for the future. Challenges such as rising interest rates, climate change and geopolitical conflicts require proactive measures. Thus, accurately predicting bank revenue plays a crucial role in aiding banks in determining which strategies to implement and at what scale. Hence, this paper examines what bank-specific determinants influence revenue forecasting and prediction across different customer segments in Sweden using machine learning algorithms such as XGBoost and Random forest. Additionally, it analyses whether there are distinct features influencing revenue among the segments and how macroeconomic indicators contribute to enhancing the accuracy of revenue forecasts. This study utilizes a dataset spanning from 2019 to 2023 provided by a major Swedish bank. The main findings of this paper is that the key drivers of bank revenue forecasting across all customer segments include "transaction amount," "maximum limit amount," "age," "consumer loan application amount," and "probability of default." Furthermore, it was found that macroeconomic determinants do not significantly enhance the accuracy of revenue forecasting. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9176860
- author
- Tran, Julia LU and Tieu, Cindy LU
- supervisor
- organization
- course
- DABN01 20241
- year
- 2024
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- machine learning, bank revenue, macroeconomic indicators, revenue forecasting, revenue prediction
- language
- English
- id
- 9176860
- date added to LUP
- 2025-02-13 08:54:37
- date last changed
- 2025-02-13 08:54:37
@misc{9176860, abstract = {{For banks to remain resilient in times of economic instability, and what the Chair of the Supervisory Board of the European Central Bank refers to as; “radical uncertainty”, it is essential for banks to plan for the future. Challenges such as rising interest rates, climate change and geopolitical conflicts require proactive measures. Thus, accurately predicting bank revenue plays a crucial role in aiding banks in determining which strategies to implement and at what scale. Hence, this paper examines what bank-specific determinants influence revenue forecasting and prediction across different customer segments in Sweden using machine learning algorithms such as XGBoost and Random forest. Additionally, it analyses whether there are distinct features influencing revenue among the segments and how macroeconomic indicators contribute to enhancing the accuracy of revenue forecasts. This study utilizes a dataset spanning from 2019 to 2023 provided by a major Swedish bank. The main findings of this paper is that the key drivers of bank revenue forecasting across all customer segments include "transaction amount," "maximum limit amount," "age," "consumer loan application amount," and "probability of default." Furthermore, it was found that macroeconomic determinants do not significantly enhance the accuracy of revenue forecasting.}}, author = {{Tran, Julia and Tieu, Cindy}}, language = {{eng}}, note = {{Student Paper}}, title = {{Uncovering Underlying Determinants of Bank Revenue}}, year = {{2024}}, }