Types of Visualisation

Last week in class we learned about how data can be visualised in ways to make data more readable. Large clumps of data are far too complex to understand initially, this is why we use charts and graphs to utilize and understand these data sets. Descriptive and inferential statistics are used to show relationships of different variables.

Big Data makes data handling and visualisation simple and it is the most accurate it has ever been. Since Big Data has surfaced, new ways of visualising data has emerged to handle the larger sampler sizes. Traditionally, data would be interpreted using small scale graphs using pen and paper, however the advancement of computers allows us to interpret data in ways never seen before, revolutionising the process entirely! How cool is that?

Here are a few examples:

Basic Line Chart

Bar graph with negative stack

3D Column Chart

Map Demographics

Overall, these data sets would not have been made possible before due to the limited sample size and inefficient data collection methods. These visualisations help display data in a manner that is readable and consistent in a relevant format, allowing new predictions and theories to be created. The larger sample sizes also means information is more accurate and reliable. I am excited to see what new methods of visualisation will arise in the near future.

References:

https://www.highcharts.com

https://ilearn.fife.ac.uk/course/view.php?id=9751#section-15

The Future Applications of Big Data

In class we learned about how Big Data can be utilized in future settings. Seeing the current trajectory and importance of Big Data, it shows no signs of slowing down. It's prevalence today is undeniable, but what part will it play in the future? How and why will Big Data remain relevant in a fast moving world? 

One area that Big Data plays a big part in future applications would be the political scene. Users' clicks and likes can indicate their voting pattern, predicting the most likely candidate based on similar users interests. Big Data undoubtedly played a key part in the recent American election where it was neck and neck. Big Data can highlight areas with strong opinions, and even attempt to sway voters using targeted adverts and subliminal messaging. It can even sway people to vote for corrupt politicians! How cool is that?

Big Data exceeds in analytics and data analysis. This can be used to predict future trends which is especially useful for businesses and marketing. Modern day businesses are fiercely competitive, and getting the upper hand is crucial for small businesses. By finding out what consumers want in an ever changing climate, businesses can take advantage of these trends and make more profit. One example would be face masks during the COVID-19 pandemic. Companies would have been made aware from analytics and clicks on social media and e-commerce sites. Big Data can allow businesses to get an early lead ahead of the competition.

Predictive analytics are essential for future applications in modern society as a whole, allowing the government to find key areas for future development, for example housing and new institutions. It can find out what users would like to see, their hobbies, and their spending habits. This lets the government cater to their citizens needs and wants allowing society to grow and prosper. 

References:

https://ilearn.fife.ac.uk/course/view.php?id=9751

Growth of Big Data

The scale of big data is unprecedented and the rate it is being collected is faster than ever. When early computers were first produced, kilobytes were the biggest form of memory used. Now, computers can have storage in terabytes, not including any of the other components. Other units of measuring memory are as follows:

• Nibble
• Byte
• Kilobyte
• Megabyte
• Gigabyte
• Terabyte
• Petabyte
• Exabyte
• Zettabyte
• Yottabyte
• Brontobyte

The size of the internet and all its data is estimated to be around 175 Zettabytes, and is expected to increase not just in size, but velocity as well. The rapid production of mobile devices has contributed to this surge. Furthermore, the globalization of technology means that even those in poorer parts of the world can now access the internet. People could even be reading this blog in rural India! How cool is that? 

The COVID-19 Pandemic also contributed to the growth of big data, as everyone was stuck indoors with nothing to do. People had to find new ways to entertain themselves, whether it was making videos, playing online games, or even creating blogs! All of these fed into the data pool, causing an unforeseen influx of memory.

References:

https://ilearn.fife.ac.uk/course/view.php?id=9751#section-4

Historical Developments of Big Data

Last week in class we learned about how Big Data originated. It was first conceived by John  R. Mashey in the 90's, although the term is generally agreed to have been used first by Roger Mougalas in 2005. 

Despite this, ancient civilisations such as the Mayans used to record data using tally sticks. Other inventions such as the abacus made calculations easier. Early libraries emerged as a way to collect and store information. As time went on, the progression and development of Big Data grew exponentially. It surpassed an individuals ability to process information, and was even utilised in World War 2 to crack the enigma code used by the Axis! How cool is that?

The progression of Big Data is measured in phases. These include:

Phase 1.0 (1970-2000)

This is where data is collected in databases and data warehouses. It collected personal information and allowed summaries to be drawn between statistics. Early data mining started to take place although it took a couple of decades to reach its full potential.

Phase 2.0 (2000-2010)

This looked at websites and analysed clicks made by users on websites. This surge of data also meant that greater amounts of storage were required. This stage also introduced software such as Apache Hadoop. This 'data pool' stored large quantities of data that users could access. Social media and networking was starting to pick up which meant data was being produced faster than ever before, more and more storage space was required, it was growing exponentially.

Phase 3.0 (2010-Present)

This phase peaked when mobile devices became commonplace. People use their phones in everyday life, this allows researchers to track peoples hobbies and habits. This behaviour can be predicted, and businesses can use targeted adverts on consumers, based purely on their preferences. 

References:

https://ilearn.fife.ac.uk/course/view.php?id=9751#section-4

Definition of Big Data

Welcome to my Big Data blog in which we are learning about Big Data. Going into it, I have a rough concept of the ideas surrounding Big Data but uncertain about how it works or why it is so prevalent in today's setting. 

Today we were introduced to Big Data. We learned that it is the large scale collection of data from individuals apps, websites, and the internet. This allows information is gathered, collected, and compared. Information is stored in the large scale data lake and is capable of building profiles on users based on their clicks, searches, and interests. Comparisons can be made using predictive analytics, which draws information from the data pool. Data can also be sold to advertisers, allowing targeted adverts with relevant products to be promoted.

Overall, Big Data takes data that would be useless on it's own, and extracts its value which can then be applied to a multitude of problems that's impossible for humans to solve on their own. How cool is that?

I am excited to learn more about the applications of Big Data, how it is used, and why it is so important in shaping modern society.

References:

https://ilearn.fife.ac.uk/course/view.php?id=9751#section-3