Slide 1

Hello and welcome, my name is Sibi Balaji and today I will be presenting to you the
results of the Data Analytics task.

Slide 2
Today's agenda will be as follows:

1. We will recap the overall project to give a high level understanding of the
business problem we're tackling and the specific requirements.
2. We will dive into the specific problem that we, the Data Analytics team, have
been focusing on and will give some background as to why this is such a big
problem.
3. After introducing the problem, I will go over the team responsible from our side
in tackling this task.
4. I will then go over the high-level process that we followed to complete this
task, so that you have complete clarity in how we tackle these kinds of tasks.
5. Finally, I will go over the all important results and I will present them as a
series of insights and visualizatio's from our analysis.

To wrap up, I will summarize and open for any questions.

Slide 3
To kick things off let me recap this engagement.

We, Accenture have embarked on a 3 month pilot with Social Buzz to focus on 3 main
tasks, aligned with some of the biggest challenges that you're currently facing.

Social Buzz has reached huge scale in recent years to become recognized as a global
unicorn company. We are here to help you manage this scale and to guide you in the
right direction.

Firstly, we will be doing an audit of your big data practice and sharing best
practices and industry expertise. Secondly we will be guiding you through a
successful IPO, of which we have deep expertise and knowledge of within our team.
And finally, we have conducted an analysis of your data to find insights regarding
your top 5 most popular categories of content

Slide 4
Focusing on the last point that I mentioned there, this is what the Data Analytics
team has been specifically focused on.

Clearly with such grand scale, this comes with a lot of data and with such vast
amounts of data comes challenges.

To give a background on how much data you've been creating:

In this day and age, content is king. Just look at some of the biggest platforms in
the world, for example YouTube, Facebook and Netflix... they are all content
businesses...

But how to capitalize on it when there is so much?

It's not just all about harvesting as much content as possible... The real value is
in understanding and crunching this content to gain a deeper understanding of your
audience and to therefore provide a more personalized and enjoyable experience.
And this is where out data analytics expertise comes in, with the insights that
we've uncovered from this task, we can show you exactly how to take analytics to
production at scale.

Slide 5
Talking about experience, we have a large data analytics practice at Accenture but
we had a team of 3 people primarily focusing on this task. Andrew Fleming is our
Chief Technical Architect and his expertise really helped to guide the team to
produce high quality analysis.

Marcus Rompton, a senior principal has worked with the worlds biggest clients on
solving their data problems and was heavily involved in the data engineering side
of this project.

And finally myself, Sibi Balaji, who was solely responsible for taking leadership
guidance and delivering high quality insights from the raw datasets and turning
these into business decisions.

Slide 6
So, how did we tackle this problem?

Well we approached it in 5 steps:

1. Data understanding - the key to success on any data project is to understand the
data in detail. So we took the time to understand the data model and domain of your
business.
2. Data cleaning - after understanding your business, we then cleaned the available
datasets and thought about what an ideal dataset should look like for this problem.
3. Data modelling - After ensuring the data was clean for analysis, we needed to
process and model this data into a dataset that can precisely answer the business
questions and produce the results needed.
4. Data analysis - With our new dataset, we used our analytical expertise to
uncover insights from this dataset and to produce visualizations to describe the
insights.
5. And finally we used these insights to unlock business decisions and to make
recommendations on next steps.

Slide 7
From your data we found that you had a total of 16 unique categories of posts
across your sample dataset. This includes things such as Food, Culture and Sport.

As well as this, there were 1897 reactions from just the animal category alone!
People obviously really like animals!

And also the most common month for users to post within was January. This aligns
with seasonal trends of social media users that feel the need to reconnect with
people after calendar events such as Christmas.

But now, onto the main question... which is... what were the top 5 most popular
categories of posts?

Slide 8
From our analysis, you can see that the top 5 most popular categories of posts were
animals, science, healthy eating, technology and food in descending order.

Animals had an aggregate popularity score of around 74965. It is very interesting

Finally, its also interesting to see science and technology too. This may suggest
that people enjoy consuming factual content and snippets of content that they can
learn something from.

Slide 9
Additionally, you can see from this chart the % split of popularity between the top
5 categories. There is not much difference between the share of each category,
however, the difference between the 1st most popular, animals and the 2nd most
popular, science, is the largest gap equal to 1.1%.

In business terms, this could suggest that the most popular category, animals, is
tailing away from the rest of the categories and may continue to get more and more
popular. To avoid an issue where 1 content category consumes the entire platform,
it will be important for you to ensure that any algorithms used to govern the
content on the platform gives a fair balance to the content categories.

Slide 10
So to summarize:

We tackled this task and found the top 5 most popular categories as asked, but we
also went one step further.

- We found that animals and science are the two most popular categories, suggesting
that users like "real-life" and "factual" content

- We also found that food was a common theme amongst popular content and the most
popular food category was healthy eating. This could be a signal to show the types
of people that are using your platform, and you could use this insight to boost
engagement even further. For example, you could run a campaign with content focused
on this category or work with healthy eating brands to promote content.

- As much as this analysis was insightful, we are ready to take it to the next
stage and we have the expertise within Accenture to help you realize these kinds of
insights in production across your organization and in real-time. We would love to
help you with this.

Slide 11
Thank you very much for listening, please feel free to ask any questions that you
may have!