Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Behavioral Targeting in E-Commerce Through the Use of Reinforcement Learning
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 thesisAlternative title
Beteendebaserad marknadsföring i e-handel genom förstärkningslärande (Swedish)
Abstract [en]

E-commerce websites often seek to maximize sales by employing sales agents to talk on the phone with selected visitors and assist them in making a purchase, and in order to make the most out of this investment, visitors must be targeted with contact offers intelligently. One approach to designing a targeting strategy is to have human experts define sets of rules that decide how to act, however, a more automated approach would be desirable. This thesis investigates a reinforcement learning approach to generating a targeting strategy. More specifically, the batch reinforcement learning algorithm fitted Q-iteration (FQI) is applied to clickstream data from a large E-commerce website to generate a targeting strategy, which is then evaluated both on historical data and in the live environment, and its performance is compared to the rule based system currently in use. Results show that the strategy generated by the FQI algorithm produces total conversion rates similar to that of the rule based system, however, it also shifts more of the sales towards the sales agents, which is undesirable.

Abstract [sv]

Inom e-handel är det vanligt att hemsidor försöker öka sin försäljning med hjälp av försäljningsagenter som kan hjälpa besökare att göra köp via telefon. För att en sådan tjänst ska vara lönsam så måste man på ett intelligent sätt välja vilka besökare som erbjuds tala med en försäljningsagent. Ett sätt att skapa en sådan strategi är att låta experter definiera regler som väljer när besökare ska erbjudas hjälp, men en mer automatiserad metod är önskvärd. Denna rapport undersöker hur förstärkningslärande kan appliceras för att lösa detta problem. Algoritmen Fitted Q-Iteration (FQI) tillämpas på klickströmsdata från en populär e-butik, och den resulterande strategin utvärderas och jämförs med den regelbaserade strategin som för närvarande används. Resultaten visar att den FQI-genererade strategin uppnår samma konverteringsgrad som den regelbaserade strategin, men samtidigt så flyttar den en del av försäljningarna till försäljningsagenterna, vilket är oönskat.

Place, publisher, year, edition, pages
2019. , p. 38
Series
TRITA-EECS-EX ; 2019:667
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-265003OAI: oai:DiVA.org:kth-265003DiVA, id: diva2:1376711
External cooperation
Now Interact Nordic AB
Supervisors
Examiners
Available from: 2020-01-20 Created: 2019-12-10 Last updated: 2020-01-20Bibliographically approved

Open Access in DiVA

fulltext(760 kB)9 downloads
File information
File name FULLTEXT01.pdfFile size 760 kBChecksum SHA-512
1074fd0d4649cec855b99df666b97435b6a4f9cdfa1aa87c065a8286b77b536eae6bb2c1f4f49ff76722de4493bb4627aa24c1b19176ef6e1a7e9f7097130889
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: 9 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: 45 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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