BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:2a7e802c7e416b5a5c3804c30088cc5a
DTSTAMP:20260309T062644Z
SUMMARY:CS MSc Thesis Presentation 17 March 2026
DESCRIPTION:Kontakt: birger.swahn@cs.lth.se\n\nTuesday\, 17 March there wil
 l be a master thesis presentation in Computer Science at Lund University\,
  Faculty of Engineering.The presentation will take place in E:2116.Note to
  potential opponents: Register as an opponent to the presentation of your 
 choice by sending an email to the examiner for that presentation (firstnam
 e.lastname@cs.lth.se). Do not forget to specify the presentation you regis
 ter for! Note that the number of opponents may be limited (often to two)\,
  so you might be forced to choose another presentation if you register too
  late. Registrations are individual\, just as the oppositions are! More in
 structions for opponents are found here on the LTH thesis project page.10:
 15-11:00 in E:2116Presenters: Magnus Herstedt\, Martin FredlundTitle: Eval
 uating Database Types for AI Chatbot Data RetrievalExaminer: Per Andersson
 Supervisors: Lars Bendix (LTH)\, Per Fryking (Lime Technologies)Customer R
 elationship Management (CRM) solutions increasingly integrate AI chatbots.
  The requirements for information retrieval are complex\, making the selec
 tion of the optimal database type critical. This thesis analyzes how diffe
 rent database types compare in their retrieval capabilities within a CRM c
 ontext.&nbsp\;This thesis was divided into two phases\, first we conducted
  interviews with stakeholders to gain insight into use cases and system re
 quirements. These insights were utilized in phase 2 that was an experiment
 al phase over four iterations in which each completed iteration was evalua
 ted and new exploratory ideas were carried on.The results demonstrated tha
 t while graph databases generally delivered strong overall performance and
  high accuracy by utilizing graph traversal\, vector databases outperforme
 d them in specific use cases specifically on retrieval from unstructured d
 ata and semantic queries. Furthermore\, the evaluation demonstrates that m
 inimizing tool calls is the most critical factor for designing an efficien
 t retriever.&nbsp\;&nbsp\;\n\nMer information om händelsen: https://www.c
 s.lth.se/evenemang/cs-msc-thesis-presentation-17-march-2026
DTSTART;TZID=GMT:20260317T091500
DTEND;TZID=GMT:20260317T100000
LOCATION:E:2116
END:VEVENT
END:VCALENDAR