In my first post, I explained my background and how I switched my career into data analytics. But before diving into it and becoming more technical, let me explain to you what it takes to speak the language of data.
Why data analytics is so important
“Data Science” is the marriage of the ancient science of Statistics with the modern one of Computer Science. Statistics is the discipline that concerns the collection, organization, analysis, interpretation and presentation of data and computers came to the scene and helped automate these processes.
Technologies that collect data are witnessing exponential growth and more and more organizations are discovering the power of data. It’s estimated that in the last two years alone, the astonishing 90% of the world’s data has been created. Businesses use it to improve the delivery of their products and services to clients, to better manage their workforce, to improve business processes that will reduce the waste of money and in general to make smarter business decisions.
Need for specialist
With such an overflow of data, there is a huge need for a workforce that will be able to manage/interpret this data. It’s important to get the right answers from the information, otherwise, you can make wrong and costly decisions. That’s when the term Data Literacy comes into play. It’s the ability to read, write and communicate data. So basically, the same functions as in any other language one could learn.
Read
Before anything, it’s important to explore and understand the data. Ask questions like:
- Are you familiar with the data?
- What are the data types of my data set? Are they numeric/quantitative or categorical/qualitative?
- What is the aggregation level of my data, the minimum and the maximum values?
- Do you see any pattern in your data?
Write
Once familiar with the data, prepare it for the next step:
- Clean it and make it homogenous.
- Filter it to remove the unnecessary elements.
- Blend it with other datasets to add additional insights to your data.
- Aggregate it to the appropriate level.
- Pivot the orientation of the tables.
- Think of specific questions you want to answer.
- Use technologies like Alteryx, Tableau Prep and SQL to perform these tasks.
Communicate
All the previous steps are gonna be useless if you keep it a secret. It’s important to transform this information into meaningful insights and present them in a beautiful dashboard. In order to be successful in your communication:
- Think of your audience, what’s their knowledge about the topic, what they want to know and until what level of detail.
- Choose the right way to represent your data (bar chart, scatterplot, etc.) and make sure it’s not misleading (omitting baseline, unsynchronised axis, etc.).
- Tell a story. Knowing the data is knowing the facts. Ask ‘why’ is something happening and translate the language of data to the language that everyone will understand.
- Use Tableau and Power BI to visualise your data.
In my next blogs, I’m gonna dive deeper into the technicalities of reading, writing and communicating data and how to achieve it using technology.
Sources
- https://www.forbes.com/sites/gilpress/2013/05/28/a-very-short-history-of-data-science/?sh=36b34db155cf
- https://en.wikipedia.org/wiki/Statistics
- https://techjury.net/blog/how-much-data-is-created-every-day/#gref
- https://www.gartner.com/smarterwithgartner/a-data-and-analytics-leaders-guide-to-data-literacy/