| Author: | Law, Kin Sang |
| Title: | Knowledge driven decision analytics for corporate client relationship management |
| Advisors: | Chung, Fu-lai Korris (COMP) |
| Degree: | Eng.D. |
| Year: | 2020 |
| Subject: | Banks and banking -- Computer network resources Customer relations -- Management -- Data processing Bank management Hong Kong Polytechnic University -- Dissertations |
| Department: | Faculty of Engineering Department of Computing |
| Pages: | xi, 116 pages : color illustrations |
| Language: | English |
| Abstract: | Although the corporate relationship manager seems to be the key enabler in commercial banking, the personal relationship sales model is not a sustainable model for the paradigm shift in digital financial markets. An efficient and effective decision-making process is one of the critical success factors of a bank. In this research, we propose an AI-driven customer relationship management (CRM) model, which adopts the latest technologies of artificial intelligence and machine learning to support the overall business decision-making by capturing and analyzing unstructured data from both internal data sources and the public domain. The proposed AI-driven CRM model represents a transformational change in integrating all business processes of the whole client journey from client onboarding to client exit. It also acts as a think tank to support the overall corporate client relationship management framework, facilitating the bank to implement knowledge driven decision analytics that articulates the bank's strategy effectively, embedding client knowledge in endÂto-end processes, maximizing the technological advantages from artificial intelligence and machine learning, and being user-friendly so that the bank can have a consistent and sustainable competitive advantage. However, most of the corporate client documents processed in commercial banks are not well-structured and the traditional analysis approach does not consider the document structure, which carries rich semantic information. In order to benefit from the business knowledge embedded in the banking documents, we propose a flexible document structure-based text representation approach in predictive analytics of unstructured data to improve the performance in the corresponding document classification task. The proposed approach significantly outperforms the traditional whole document approach which does not take into considerations of the document structure. To further enhance the performance of document classification, different kinds of auxiliary information, including company website and industry reports, are captured, processed and incorporated. A mild increase in classification performance is achieved by incorporating industry information in the classification task. Other than classification, the document structure-based text representation approach is also applied in sentiment analysis and clustering to generate more insights for business planning and decisions. Furthermore, different use cases adopting the proposed methods and models are discussed, demonstrating the ways of applying predictive analytics to improve the corporate client relationship management process, including information retrieval of commercial lending documents to support industry-level sales planning, client relationship strategy formulation to improve customer engagement, clients' portfolio monitoring through business alert triggers to facilitate proper risk management, and document clustering to identify new business opportunities. With the proposed AI-driven CRM framework, knowledge can be effectively and efficiently used for business decisions and planning so as to improve the competitive advantage and substantiality of banks. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5095.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.89 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10672