University of Twente Student Theses
Hybrid Machine Learning (ML) Models in Banking : An Approach for the B2B Sector
Dhawan, Sonakashi (2023) Hybrid Machine Learning (ML) Models in Banking : An Approach for the B2B Sector.
|
PDF
5MB |
| Abstract: | The advent of big data has revolutionized decision-making processes within the Business-to Business (B2B) financial sector, primarily by leveraging the predictive power of Machine Learning (ML) models. This study investigates the development of innovative Hybrid Model (HM)s tailored for predicting future investments in the B2B banking sector. By comparing HMs with traditional models such as Extreme Gradient Boosting (XGBoost) regressor, the study highlights the superiority of HMs, for example, the ones employing k-means clustering, in terms of performance metrics. Furthermore, it uses Explainable artificial intelligence (XAI) techniques such as SHapley Additive exPlanations (SHAP) to increase the transparency and explainability of ML decisions, enhancing trust in automated financial forecasting. A comprehensive analysis reveals the effectiveness of HMs models over traditional ML methods, underscoring the potential of such HMs in reshaping the future of financial services. This research bridges a critical gap by providing empirical evidence on the efficacy of HMs, contributing to academic literature and offering a practical blueprint for financial institutions aiming to adopt advanced analytics in their operational strategies. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Business Information Technology MSc (60025) |
| Link to this item: | https://purl.utwente.nl/essays/97697 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page