Business Information Systems - A/B Testing of Webpages Report

This report explores the application of A/B testing to improve website performance. It begins with an introduction to the concept, emphasizing the importance of A/B testing in optimizing website monetization and user experience. The report delves into what aspects of a webpage can be tested, focusing on the value proposition and its significance in search engine optimization. It also examines the role of hypotheses in the testing process, comparing different webpage versions, and determining the necessary customer sample size for accurate results. The report then discusses the A/B testing team composition, along with the advantages and disadvantages of the method, and explores multivariate testing. Practical examples of comparisons using the Kaplan Business School webpage are provided, along with a discussion of the conversion funnel stages: awareness, consideration, conversion, and loyalty. Finally, the report highlights two A/B testing software packages, Maxymiser and Adobe Target, and concludes with a summary of key findings and references.

Business Information System 1
Business Information System
Student
Course
Tutor
Institutional Affiliations
State
Date

Business Information System 2
Introduction
As more and more websites are developed, the competition for internet users is becoming
more intense. It has, therefore, become extremely difficult for website developers to get people
to a site and direct them to do what is best for the business on the website. Despite the fact that
there is massive data on the internet about everything done by all internet users, the data can be
harnessed to satisfy the needs of an organization. A/B testing constitute a method of comparing
two or more different variations and optimizing a website’s performance using the data. The
primary focus of this article will be on how the performance of a website can be improved by
A/B testing.
As the thesis will explore the stated objective, it will attempt to solve the following
problems that have become common in internet marketing:
a) Monetization is not optimized to for its maximum potential.
b) Users visit wrong places on the internet while browsing.
The A/B testing has become one of the most prominent testing methods as it enables
website administrators to find direct data about the actions of its users. A/B can help to improve
a website’s performance in various aspects.
What aspects of a page can you test using A/B testing?
Various aspects will be tested in the A/B test, the major aspect that must get tested is the
value proposition (Zhu et al., 2013, pp. 320-323). Many people often think of value proportion
as one statement on a website, however, it is beyond that as it should be conveyed the copy,
image and various web page elements inclusive of landing pages.

Business Information System 3
How does it relate to webpage and search engine optimization?
A unique value proposition is a key element to the google search engine. Due to the fact
that google process trillions of searches every year equating to billions of searches a day, there is
no guarantee that an organization’s web page can be displayed on a topmost section of the page
(Kang, Liu, Rexford, and Walker, 2013, pp. 13-24). As the google does not consider what to
display on top of its page, the value proposition will be of great significance since it will ensure
that an organization’s page appears at the top most of the screen to attract more customers.
What is the role of hypotheses in this optimization process?
The hypothesis is an essential procedure in the A/B test. Therefore it cannot be left out in
the study. Hypothesis test help in evaluating the two statements that are mutually exclusive, it is
all about determining which statement is best supported by a sample data.
How are pages compared?
Pages will be compared by running the experiments on the server and redirect visitors
using HTTP 302 redirects as an example. However, if running the experiment is impossible
redirects will be performed in JavaScript.
How many customers do you need for the comparison?
Due to the fact that A/B testing analyses the estimated number of customers of the
particular website getting optimized to make a statistical prediction about the group as a whole,
the test should be more accurate. The larger the number the more the accurate the test is, it is
therefore imperative that the largest number possible to be used in order to enhance accuracy
which is the main goal of the test.

Business Information System 4
Who would be in the A/B testing team?
Implementation of the A/B testing needs the commitment of internal resources and at a
minimum, in some sense, building a team which helps in running and reporting a test. However,
while building a team, the following must be taken into consideration. Everyone is on the team,
the active team is kept focused (Dulloor, et al., 2014, p. 15).
What are the advantages and disadvantages of A/B testing?
Like everything else, A/B also has its advantages and disadvantages. The advantages
include: it gives early feedback, and low barrier entry (Bao, 2007, pp. 501-510). The limiting
factors, on the other hand, are that A/B test bust be subject to the same variables to give
feedbacks which are reliable, also, its accuracy diminishes with an increase in the number of
variables.
What is multivariate testing?
Multivariable refer to a testing hypothesis where multiple variables are modified
(Saccenti, Hoefsloot, Smilde, Westerhuis, and Hendriks, 2014, pp.361-374).
Examples of the specific comparisons I could make from the Kaplan Business School
webpage and the intention behind them.
Case 1: Having an increase of leads after optimizing the Kaplan Business School webpage
In that case, my hypothesis would be creating a user-friendly website with a click-
through menu will improve the conversation between the organization and the website users. The
result would be: conversation increased after a new user-friendly website is created.

Business Information System 5
Case 2: Kaplan Business School webpage wants to increase its CRT by adding text in their
call to action button
My hypothesis, in this case, would be: making a text i.e. “Add to Cart” in the call to
action button will lead to an increase in people adding items to shopping carts. The result should
show an increase in percentage was recorded in CRT by adding the text instead of using image
alone.
Two software packages for A/B testing
Maxymiser is one of the software that aids in A/B test. The software is a powerful tool for
optimizing customer experience as well as the creation of the sophisticated campaigns. Another
powerful A/B testing tool is Adobe Target (Poppendieck, and Cusumano, 2012, pp.26-32). This
software offers an intuitive user interface to develop personalized web experience quickly, create
the A/B test as well as confidentiality target content.
The conversion funnel
 Awareness: the main goal at this stage is to show the value of the product or service to
consumers (Bagherjeiran, Hatch, and Ratnaparkhi, 2010, pp. 146-153). Educational
content is also built at this stage as the merchant build a relationship with the client. The
seller should not send content that is not applicable to the client at this stage.
 Consideration: at this point, the merchant had grabbed the attention of a prospective
client and now build a deeper relationship with the customer as the customer get
introduced to the products and services as he nurtures them with targeted or contextual
content.

Business Information System 6
 Conversion: this a stage where a merchant convinces subscriber to purchase its products
or services. It is characterized with talks about the benefits of products or services.
 Loyalty: here, the merchant retains customers (Koch, 2017). Through loyalty, customers
are delighted and with awesome product or service and helpful content. The seller should
give meaningful information to the client.
Summary
At a glance, According to the study, it can be deduced that websites can be manipulated
to suit the needs of an individual or an organization. Besides, addressing the aforementioned
problems faced by internet users, this article has described a conversion funnel demonstrating
how consumer access and buy products or services.

Business Information System 7
Reference list
Bagherjeiran, A., Hatch, A.O. and Ratnaparkhi, A., 2010, July. Ranking for the conversion
funnel. In Proceedings of the 33rd international ACM SIGIR conference on Research and
development in information retrieval (pp. 146-153). ACM.
Bao, S., Xue, G., Wu, X., Yu, Y., Fei, B. and Su, Z., 2007, May. Optimizing web search using
social annotations. In Proceedings of the 16th international conference on World Wide Web pp.
501-510. ACM.
Dulloor, S.R., Kumar, S., Keshavamurthy, A., Lantz, P., Reddy, D., Sankaran, R. and Jackson,
J., 2014, April. System software for persistent memory. In Proceedings of the Ninth European
Conference on Computer Systems (p. 15). ACM.
Kang, N., Liu, Z., Rexford, J. and Walker, D., 2013, December. Optimizing the one big switch
abstraction in software-defined networks. In Proceedings of the ninth ACM conference on
Emerging networking experiments and technologies (pp. 13-24). ACM.
Koch, O.F., 2017. Nudges as Conversion Funnel Enhancers in Digital Business
Models (Doctoral dissertation, Technische Universität).

Business Information System 8
Poppendieck, M. and Cusumano, M.A., 2012. Lean software development: A tutorial. IEEE
software, 29(5), pp.26-32.
Zhu, J., Chan, D.S., Prabhu, M.S., Natarajan, P., Hu, H. and Bonomi, F., 2013, March.
Improving web sites performance using edge servers in fog computing architecture. In 2013
IEEE Seventh International Symposium on Service-Oriented System Engineering (pp. 320-323).
IEEE.