February 22, 2020 Thesis Open Access

Getachew Gemechu

JSON-LD (schema.org) Export

{
  "description": "<p>Direct marketing is a form of communicating an offer directly to a targeted group of<br>\ncustomers through a variety of media. It plays a major role in customer retention and<br>\nservice provisioning tasks. Retaining customers by providing products and services that<br>\nmeet their need is one of the main objectives of customer relationship management. Identifying<br>\nprospective customers for direct marketing enables a company to reach specific<br>\naudiences which will more effectively respond to promotions. Moreover, direct marketing<br>\nhelps businesses to optimize their marketing budget, keeps current customers loyal<br>\nto them, and makes businesses capable of measuring the result obtained from promotions.<br>\nEthio telecom promotes service packages to its customers through SMS and mass communication<br>\nchannels. However, promotions should target customers based on the specific<br>\nservices they use, and customer over-touching should be reduced especially during<br>\nSMS advertisement. In the current practice, no scientific methodology is implemented<br>\nto estimate the potential respondents to cross-selling market promotion. Promotions are<br>\ncommunicated to both potential buyers and non-buyers without distinguishing the two<br>\ngroups. Direct marketing approaches help the company to effectively allocate resources<br>\nand give services based on the interests of customers.<br>\nThe aim of this thesis is to identify prospective customers in ethio telecom mobile valueadded<br>\nservice market. To achieve this goal, five classifiers namely Naive Bayes, Neural<br>\nnetwork, SVM, K-nearest neighbour, and Decision tree (J48) tested with customers<br>\nservice usage historical data. In this process, 900,000 customers&rsquo; actual CDRs from<br>\nethio telecom were gathered and raw data aggregated with the aim of representing users&rsquo;<br>\nbehaviour. The representation was based on users&rsquo; responses towards service fee and<br>\ntime preference to use services. Sixteen feature variables and one predictor variable<br>\nare constructed from the raw CDR collected. Data cleaning and class balancing done,<br>\nand the selected classifiers tested for their accuracy in identifying prospective buyers of<br>\nservice packages</p>", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "creator": [
    {
      "@type": "Person", 
      "name": "Getachew Gemechu"
    }
  ], 
  "headline": "Performance Comparison of Classifiers for Prospective Buyers Identification in ethio telecom Mobile Cross-Selling Market", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2020-02-22", 
  "url": "https://nadre.ethernet.edu.et/record/4920", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.20372/nadre:4920", 
  "@id": "https://doi.org/10.20372/nadre:4920", 
  "@type": "ScholarlyArticle", 
  "name": "Performance Comparison of Classifiers for Prospective Buyers Identification in ethio telecom Mobile Cross-Selling Market"
}