Increasing e-commerce conversion rate with relevant search results using Elasticsearch
Linnusmäki, Toni (2020)
2020
Tietojenkäsittelyopin maisteriohjelma - Master's Programme in Computer Science
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2020-05-22
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202004294609
https://urn.fi/URN:NBN:fi:tuni-202004294609
Tiivistelmä
Search engines have grown vastly and are now part of our everyday life by providing more straightforward navigation on the internet. Besides, search engines are an integrated part of many websites, including e-commerce platforms. In this thesis, the focus was to increase the relevance of the search results of an existing e-commerce platform and analyze how the conversion rate is affected. Furthermore, the conversion rate describes the percentage of visitors that bought something from the total number of visitors on a website, and it is a widely used measurement in e-commerce.
Previous research has focused mostly on studying different ranking algorithms, but not many are included in the existing search engine frameworks. For this thesis, the purpose was to investigate how the methods from previous research could be utilized in an e-commerce platform with real customers. Furthermore, the conducted tests were over six weeks and included tens of thousands of customers.
The data that was collected during the testing phases of the proposed methods shows how the changes affect the conversion rate of the e-commerce platform. In addition to the conversion rate, the click-through rate was analyzed since it seemed to capture the changes better. The results include both measurements and analysis of how the different parts possibly affected the measurements.
While the results did not indicate that the conversion rate of the e-commerce platform was increased by the proposed methods, the results showed that with a simple solution, the existing process could be replaced. In addition, the results showed the need and direction for future development, which could have a further effect on the conversion rate of an e-commerce platform.
Previous research has focused mostly on studying different ranking algorithms, but not many are included in the existing search engine frameworks. For this thesis, the purpose was to investigate how the methods from previous research could be utilized in an e-commerce platform with real customers. Furthermore, the conducted tests were over six weeks and included tens of thousands of customers.
The data that was collected during the testing phases of the proposed methods shows how the changes affect the conversion rate of the e-commerce platform. In addition to the conversion rate, the click-through rate was analyzed since it seemed to capture the changes better. The results include both measurements and analysis of how the different parts possibly affected the measurements.
While the results did not indicate that the conversion rate of the e-commerce platform was increased by the proposed methods, the results showed that with a simple solution, the existing process could be replaced. In addition, the results showed the need and direction for future development, which could have a further effect on the conversion rate of an e-commerce platform.