<?xml version="1.0" encoding="UTF-8"?>
<mods xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" version="3.1" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
  <titleInfo>
    <title>Prediction on online retail customer segmentation with rfm model-based in malaysia using machine learning</title>
  </titleInfo>
  <name type="personal">
    <namePart>Muhammad Isyhraf Azmin</namePart>
    <role>
      <roleTerm authority="marcrelator" type="text">creator</roleTerm>
    </role>
    <role>
      <roleTerm type="text">author.</roleTerm>
    </role>
  </name>
  <typeOfResource manuscript="yes">text</typeOfResource>
  <originInfo>
    <issuance>monographic</issuance>
  </originInfo>
  <language>
    <languageTerm authority="iso639-2b" type="code">eng</languageTerm>
  </language>
  <physicalDescription>
    <form authority="marcform">print</form>
    <extent>xiv, 100 pages : Illustrations (some colour) ; 1 CD-ROM.</extent>
  </physicalDescription>
  <abstract>This research looks at the impact of e-commerce on consumer behaviour and tries to establish  effective marketing strategies through customer segmentation and analysis. Data-driven  methodologies like RFM modelling, k-means clustering, and decision tree modelling provide  useful insights into client behaviour, loyalty levels, and purchase patterns. RFM ratings are used  to create unique customer categories, demonstrating considerable differences in terms of recency,  frequency, and monetary values. The decision tree model outperforms other models in properly  forecasting client classes, offering useful insights into the distribution and characteristics of  various consumer groups. The investigation yielded practical recommendations such as the  deployment of personalised marketing tactics that respond to the individual demands and  preferences of each consumer category. This includes building focused marketing efforts that  address the unique qualities of each group, as well as concentrating on enhancing the entire  customer experience across all touchpoints. Businesses may optimise consumer interaction,  promote revenue development, and achieve long-term success in the increasingly competitive ecommerce industry by implementing these guidelines. Furthermore, the study emphasises the  significance of data-driven decision making and ongoing customer data analysis in order to keep  up with changing consumer preferences and market dynamics. Establishing feedback systems and  responding quickly to client complaints are critical in cultivating a customer-centric culture. It is  also essential to regularly analyse and monitor consumer data in order to successfully adjust plans  to changing customer wants and market trends. Overall, this study offers significant insights and  a practical roadmap for organisations to exploit data-driven insights, allowing them to customise  their marketing strategies, efficiently satisfy client wants, and stay ahead of the changing business  landscape. Businesses may improve consumer engagement, increase revenue growth, and achieve  long-term success in the increasingly competitive e-commerce industry by applying these tips.</abstract>
  <note type="statement of responsibility">Muhammad Isyhraf Bin Azmin</note>
  <note>Center for Mathematical Sciences</note>
  <note>Bachelor of Applied Science In Data Analytics With Honour -- Universiti Malaysia Pahang – 2023</note>
  <note>Includes bibliographical references</note>
  <subject authority="lcsh">
    <name type="corporate">
      <namePart>Center for Mathematical Sciences</namePart>
    </name>
    <topic>Dissertations</topic>
  </subject>
  <subject authority="lcsh">
    <topic>Universities and colleges</topic>
    <topic>Dissertations</topic>
  </subject>
  <subject authority="lcsh">
    <topic>Final Year Report</topic>
    <topic>Dissertations</topic>
  </subject>
  <identifier type="isbn">THE0010035 (Local)</identifier>
  <recordInfo>
    <recordContentSource authority="marcorg">UMPSA</recordContentSource>
    <recordCreationDate encoding="marc">250506</recordCreationDate>
    <recordChangeDate encoding="iso8601">20251125111038.0</recordChangeDate>
    <languageOfCataloging>
      <languageTerm authority="iso639-2b" type="code">eng</languageTerm>
    </languageOfCataloging>
  </recordInfo>
</mods>
