Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective
Intelligent Financial Advisors (IFAs) in online financial applications (apps) have brought new life to personal investment by providing appropriate and high-quality portfolios for users. In real-world scenarios, identifying potential clients is a crucial issue for IFAs, i.e., identifying users who a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2022-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2021.9020021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568951087824896 |
|---|---|
| author | Qixiang Shao Runlong Yu Hongke Zhao Chunli Liu Mengyi Zhang Hongmei Song Qi Liu |
| author_facet | Qixiang Shao Runlong Yu Hongke Zhao Chunli Liu Mengyi Zhang Hongmei Song Qi Liu |
| author_sort | Qixiang Shao |
| collection | DOAJ |
| description | Intelligent Financial Advisors (IFAs) in online financial applications (apps) have brought new life to personal investment by providing appropriate and high-quality portfolios for users. In real-world scenarios, identifying potential clients is a crucial issue for IFAs, i.e., identifying users who are willing to purchase the portfolios. Thus, extracting useful information from various characteristics of users and further predicting their purchase inclination are urgent. However, two critical problems encountered in real practice make this prediction task challenging, i.e., sample selection bias and data sparsity. In this study, we formalize a potential conversion relationship, i.e., user → activated user → client and decompose this relationship into three related tasks. Then, we propose a Multitask Feature Extraction Model (MFEM), which can leverage useful information contained in these related tasks and learn them jointly, thereby solving the two problems simultaneously. In addition, we design a two-stage feature selection algorithm to select highly relevant user features efficiently and accurately from an incredibly huge number of user feature fields. Finally, we conduct extensive experiments on a real-world dataset provided by a famous fintech bank. Experimental results clearly demonstrate the effectiveness of MFEM. |
| format | Article |
| id | doaj-art-f0cd35b454344e9c96ccaeb375a4fca5 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2022-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-f0cd35b454344e9c96ccaeb375a4fca52025-02-02T23:47:26ZengTsinghua University PressBig Data Mining and Analytics2096-06542022-03-0151647810.26599/BDMA.2021.9020021Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask PerspectiveQixiang Shao0Runlong Yu1Hongke Zhao2Chunli Liu3Mengyi Zhang4Hongmei Song5Qi Liu6Department of Anhui Province Key Laboratory of Big Data Analysis and Application (BDAA), School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, ChinaDepartment of Anhui Province Key Laboratory of Big Data Analysis and Application (BDAA), School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, ChinaDepartment of College of Management and Economics, Tianjin University, Tianjin 300072, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaDepartment of Information Technology, China Merchants Bank, Shenzhen 518000, ChinaDepartment of Information Technology, China Merchants Bank, Shenzhen 518000, ChinaDepartment of Anhui Province Key Laboratory of Big Data Analysis and Application (BDAA), School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, ChinaIntelligent Financial Advisors (IFAs) in online financial applications (apps) have brought new life to personal investment by providing appropriate and high-quality portfolios for users. In real-world scenarios, identifying potential clients is a crucial issue for IFAs, i.e., identifying users who are willing to purchase the portfolios. Thus, extracting useful information from various characteristics of users and further predicting their purchase inclination are urgent. However, two critical problems encountered in real practice make this prediction task challenging, i.e., sample selection bias and data sparsity. In this study, we formalize a potential conversion relationship, i.e., user → activated user → client and decompose this relationship into three related tasks. Then, we propose a Multitask Feature Extraction Model (MFEM), which can leverage useful information contained in these related tasks and learn them jointly, thereby solving the two problems simultaneously. In addition, we design a two-stage feature selection algorithm to select highly relevant user features efficiently and accurately from an incredibly huge number of user feature fields. Finally, we conduct extensive experiments on a real-world dataset provided by a famous fintech bank. Experimental results clearly demonstrate the effectiveness of MFEM.https://www.sciopen.com/article/10.26599/BDMA.2021.9020021intelligent financial advisor (ifa)potential client identificationmultitask learning (mtl)feature selection |
| spellingShingle | Qixiang Shao Runlong Yu Hongke Zhao Chunli Liu Mengyi Zhang Hongmei Song Qi Liu Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective Big Data Mining and Analytics intelligent financial advisor (ifa) potential client identification multitask learning (mtl) feature selection |
| title | Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective |
| title_full | Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective |
| title_fullStr | Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective |
| title_full_unstemmed | Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective |
| title_short | Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective |
| title_sort | toward intelligent financial advisors for identifying potential clients a multitask perspective |
| topic | intelligent financial advisor (ifa) potential client identification multitask learning (mtl) feature selection |
| url | https://www.sciopen.com/article/10.26599/BDMA.2021.9020021 |
| work_keys_str_mv | AT qixiangshao towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT runlongyu towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT hongkezhao towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT chunliliu towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT mengyizhang towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT hongmeisong towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective AT qiliu towardintelligentfinancialadvisorsforidentifyingpotentialclientsamultitaskperspective |