Institut für Informatik | Sitemap | LMU-Portal
English
  • Startseite
  • Studieninteressierte
  • Studierende
    • Ersti Infopoint
    • Semesterplanung
    • Prüfungsleistungen und Studienordnung
    • Abschlussarbeiten
      • Bachelor
      • Master
      • Projekt
      • Freie Themen
      • Richtlinien
    • Benutzerstudien
    • Auslandsaufenthalte
    • Vorlagen
    • Glossar
    • FAQ
    • Ansprechpartner
  • Lehrveranstaltungen
  • Forschung
  • Personen
  • Kontakt
  • Besucher
  • Jobs
  • FAQ
  • Intern

Publikations-Information

Cooperation with a start-up to develop an AI-led interview flow to build trust and induce honest high-quality answers

master thesis

Status open
Advisor Thomas Weber
Professor Prof. Dr. Albrecht Schmidt

Task

Background: This is a project in collaboration with the Economics Department at the LMU and a start-up called Naven Labs. Naven Labs is developing an AI-based solution for firms to diagnose potential roadblocks in their strategy implementation and to identify effective solutions. First, AI-led interviews are conducted with decision makers in the firm, in which they are asked about barriers to strategy execution. The interviews are then analyzed and aggregated, and patterns and problem areas are identified. The AI then suggests corresponding solutions. All results are visually represented in an interactive dashboard.

Since the interview touches on sensitive topics, it is vital that the AI-led interview feels natural and fosters trust, so that the interviewee feels empowered to speak up and truthfully reveal their opinions and observations. Moreover, it needs to strike the balance between gathering enough information on a given topic and ask appropriate follow-up questions, while keeping the interview engaging, non-repetitive and stick to a given ime frame.

Tasks: In cooperation with the Economics Department and Naven Labs, your task will be to help improve the AI-led interview flow to foster trust and generate honest, high-quality answers.This includes

  • Conducting a literature research on existing resources about optimal interview design and factors increasing trust in an AI-led conversation
  • Identifying aspects of the conversation flow, style and strategy to test that are interesting both scientifically and for the start-up
  • Setting up and running an A/B-test on the identified aspect of the conversation flow and their effect on user experience, answer quality and honesty (in the field with real decision makers in firms and/or with students in the lab)
  • Designing an optimal conversation flow that solves the trade-off between a natural, pleasant conversation flow, and gathering all the necessary information
  • Supporting the start-up in the programming of the prototype
  • Documenting findings and insights in a BA or MA thesis and presenting them in the Disputationsseminar
  • Supporting the creation of a report on the findings and insights to be used by the start-up in sales pitches and their own documentation

Skills needed:

  • German language skills
  • Strong communication skills, esp. towards non-experts in the field
  • Good knowledge of Python and TS
Nach oben
Impressum – Datenschutz – Kontakt  |  Letzte Änderung am 11.04.2020 von Changkun Ou (rev 35668)