CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
User Centred design of Conversational UI for Wealth Management Customers
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Conversational UI (CUI) like voice assistant and chatbot are being introduced to provide 24x7 enquiry response, advice and technical support. This study aims at assessing User Experience related factors, which reinforce Trust between Wealth Management customer and the CUI in tasks normally performed by Relationship Managers.

Given the financial and resource constraints of the thesis, semi structured interviews and Wizard of Oz experiments were chosen as the methods of study. These methods helped in delving deep into user issues within limited time period. The study finds that investors were happy to get response in text and graphics mode but not in voice since the information was considered confindential. There were apprehensions in using chatbot for getting investment advice.

Findings of this study may be helpful to wealth management organisations in designing conversation UI strategy. However, the study was conducted with clients in India, hence the findings are more relevant to countries with similar socio-cultural conditions.

Abstract [sv]

Konversationsgränssnitt (Conversational UI, CUI) som röstassistent och chatbot tas i bruk för att ge 24x7 svar, råd och teknisk support. Denna studie syftar till att bedöma användarupplevelse-relaterade faktorer som förstärker förtroendet mellan förmögenhetsförvaltningskunder och CUI i uppgifter som normalt utförs av kundansvariga.

Med tanke på de finansiella och resursbegränsningarna i avhandlingen, valdes halvstrukturerade intervjuer och Wizard of Oz-experiment som studiemetoder. Dessa metoder bidrog till att gräva djupt in i användarproblem inom en begränsad tidsperiod. Studien konstaterar att investerare var nöjda att få svar i text och grafik, men inte i röst eftersom informationen ansågs konfidentiell. Det fanns en oro för att använda chatbot för att få investeringsrådgivning.

Place, publisher, year, edition, pages
2019. , p. 11
Series
TRITA-EECS-EX ; 2019:615
Keywords [en]
Trust, Conversational UI, Wealth Management, HCI
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-264540OAI: oai:DiVA.org:kth-264540DiVA, id: diva2:1374047
Supervisors
Examiners
Available from: 2019-11-28 Created: 2019-11-28

Open Access in DiVA

fulltext(1566 kB)8 downloads
File information
File name FULLTEXT01.pdfFile size 1566 kBChecksum SHA-512
90842d036c3bc5fca54e37fd402846e4fc418bd701e6218671dd177987a14ecee89879dc185cb20a2c3030003816facc5dec28068e7cbea828bdb4fbe47df764
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 8 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf