Fin Irjmets1655964131

e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science

( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:04/Issue:06/June-2022 Impact Factor- 6.752 www.irjmets.com
OPTIMIZING EMAIL MARKETING USING MACHINE LEARNING
Y. Satyam*1, J. Raviteja*2, D. Rithik Rao*3, R. Akhil*4
*1,2,3,4Affiliated To JNTUH, Dept. Of IT, CMR Technical Campus, Hyderabad, Telangana, India.
ABSTRACT
Email marketing is broadcasting commercial messages to a group of people using email. Currently, email
marketing is consistently delivering relatively high return on investment (ROI) in a marketing field. However,
collecting subscriber information and sending the email only to interested consumers is a major research issue
in email marketing. This paper introduces a conceptual model for an effective email marketing system
clustering and segmenting subscribers based on their activity throughout a marketing campaign. The model
consists of two main components: Collecting subscriber activity data and Clustering and Segmenting
subscribers. We performed a marketing experiment based on our model and analyzed subscriber activity data.
Using our model, the overall performance of subscriber activity was improved after sending out email
campaigns to segmented groups of subscribers based on their individual interest.
Keywords: Email Marketing, Return On Investment, Clustering, Segmenting, Email Campaign.
I. INTRODUCTION
Machine Learning and Artificial Intelligence are not completely new to email. They have been around at least
since the late 90’s. The first major adoption was a Naive Bayesian filter based on the 2002 paper “A plan for
spam”3 by Paul Graham. Spam3 filter evolution continued with advanced algorithms like neural networks,
support vector machines, relevance vector machines, etc. The marketing side of email industry was relatively
slow to embrace machine learning and AI. Even today, a lot of companies want to leverage the hype of AI and
ML, but a marketer needs to understand “How is this new technique improving my customer experience and
ROI?” If the answer is not conclusive or results are not visibly different, then the solution is just hype with no
value addition. Marketers strive to personalize emails in the quest for relevance. This is not new to seasoned
marketers who have been using marketing automation platforms to create customer journeys or leveraging
segmentation and/or personas. This is good usage of data and tools, but it simply can’t scale beyond a certain
point. In our experience, most clients have around 20-25 data segments. For relatively large user bases, too
many journeys and segmentation could potentially ruin the user experience and complex rules make it hard to
maintain. The genius of ML and AI can save the day AI power, combined with human intellect (IQ), is going to
create a hyper-personalized experience to the user which will compel them to remain engaged with the brand.
II. LITERATURE SURVEY
The widespread impacts of artificial intelligence (AI) and machine learning (ML) in all segments of society have
driven researchers to term the present day as the “AI Revolution” (Makridakis, 2017). This AI revolution has
sparked multidisciplinary research. In the business world, such processes have been impactful as a significant
source of innovation (M.-H. Huang & Rust, 2018). Despite their relevance, for many marketing researchers and
practitioners, terms such as artificial intelligence and machine learning may seem akin to terms of a foreign
language (Conick, 2017). This paper attempts to change this scenario by discussing the central role that AI and,
more specifically, ML can play as a research method in the marketing field. Why should ML be applied to
marketing? There are many possible answers to this question rooted both in academic and applied practices of
the discipline. For practitioners, for example, ML is disrupting many industries with new business models,
products, and services. In academia, the impact appears too equally substantial. For example, the lack of
generalization of scientific discoveries is at the center of the so-called “replication crisis,” which has affected
many of the life and social sciences, including the fields of management and marketing. This crisis has occurred
because researchers have found that many of the most important scientific studies are difficult or impossible to
replicate or reproduce (see, for example, Camerer et al., 2018). As this paper will discuss, the fundamental goal
of machine learning is to generalize beyond the examples provided by training data, looking for generalizability
(Domingos, 2012). Thus, one of the potential contributions of ML to marketing (and to management in general)
lies in its robustness for the generation, testing, and generalization of scientific discoveries. With these different
academic and practical perspectives in mind, the goal of this paper is to provide marketing with an overview of
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[3354]
e-ISSN: 2582-5208
ML and to analyze required learning, applications, and future developments involved in applying ML to
marketing.
III. PROPOSED METHOD
Optimizing marketing campaigns is one of the most common data science tasks. Among the many possible
marketing tools, one of the most efficient is using emails. Emails are great cause they are free and can be easily
personalized. Email optimization involves personalizing the text and/or the subject, who should receive it,
when should be sent, etc. Machine Learning excels at this.
Email marketing has four major advantages:
1) It can be lower in cost than other types of marketing.
2) Because email takes less time to create and send, marketers can communicate with subscribers more
frequently.
3) Marketers can test their email marketing campaign to know what graphics, headlines, offers and even colors
subscribers will respond to.
4) Forwarding an email with an enticing or useful offer or piece of information only takes seconds and many
users will do it.
Figure 1: Architecture
IV. RESULTS
Figure 2: User Activity

[3355]
e-ISSN: 2582-5208
Figure 3: Data Analysis of Email Marketing by country
Figure 4: Data Analysis of Email Marketing by weekday

[3356]
e-ISSN: 2582-5208
Figure 5: Prediction of Email Marketing

V. CONCLUSION
This project proposes a efficient and scalable model for effective Email Marketing. Tracking subscriber web
interaction data and email activity helped us to get more insight into prospective subscribers. Considering a
variety of aspects and narrowing down the huge set of important data into a few clustering factors rendered the
segmentation more efficient.
VI. FUTURE SCOPE
Although this paper discussed some of the most critical applications and advances of ML for marketing, many
others were not analyzed due to space limitations. This list includes applications and advances for voice
recognition, natural language processing, augmented and virtual reality, and the use of so-called “notebooks”
(open-source web applications for sharing codes and texts) that may popularize ML, among many other
features
VII. REFERENCES
[1] Radicati Team, 'The Radicati Group, Inc. Email Market, 2014-2018', Radicati.com, 2014. [Online].
Available: http://www.radicati.com/?p=12482.
[2] Benchmarkemail.com, 'What Is Email Marketing? - Benchmark Email', 2014. [Online]. Available:
http://www.benchmarkemail.com/resources/email-marketing-articles/what-is-email-marketing.
[3] D. Ryan, Understanding digital marketing. [S.l.]: Kogan Page, 2014.
[4] Marketingsherpa.com, 'New Survey Data: Email's ROI Makes Tactic Key for Marketers in 2009'
.Available: http://www.marketingsherpa.com/article/emails-roi-makes-tactic-key.
[5] Emailmarketing.comm100.com, 'The Top10 Benefits of Email Marketing', 2014.[Online].
Available:http://emailmarketing.comm100.com/email-marketing-ebook/email-marketing-
benefits.aspx.
[6] S. Jenkins, The truth about email marketing. Upper Saddle River, N.J.: FT Press, 2009.
[7] GetResponse, 'Email Marketing Secrets Guide', 2008. [Online]. Available:
http://www.getresponse.com/documents/core/white-papers/Email_Marketing_Secrets_Guide.pdf

[3357]

Fin Irjmets1655964131

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Fin Irjmets1655964131

Uploaded by

Copyright:

Available Formats

e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

Figure 2: User Activity

Figure 3: Data Analysis of Email Marketing by country

Figure 4: Data Analysis of Email Marketing by weekday

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

Figure 5: Prediction of Email Marketing

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

You might also like