If you are just starting out in data analytics and are unfamiliar with some of the basic terminology, don’t worry. At Cangler, we’ve got you covered with ten basic data analytics terms that everyone in the field should know. From the different types of data analytics, to the crossover between data analytics and machine learning, this article will serve as a necessary introduction to some of the simple, yet fundamental concepts and processes used in the field today.
This article will cover the following data analytics terms:
Data Analytics,
Descriptive Analytics,
Diagnostic Analytics,
Predictive Analytics,
Prescriptive Analytics,
Data Mining,
Cloud/Cloud-based,
Machine Learning,
Dataset,
Big Data/Big Data Analytics,
…
What is Data Analytics?
Data analytics is simply the collection, presentation, and evaluation of data to help inform decisions. This analysis could range in complexity from analyzing weather patterns to evaluating Twitter posts to predict stock market fluctuations.
Data analytics is divided into different types or processes based on the end goal of the analytics task.
What is Descriptive Analytics?
Put simply, descriptive analytics is the presentation of data in a clear and easily digestible way for your target audience. With descriptive analytics, your data is normally transformed into visuals in the form of graphs, charts, and other infographics.
While other sectors of data analytics deal with how to analyze and draw conclusions from data, the goal of descriptive analytics is simply to present your data in the most efficient medium.
This is especially important when dealing with historical business data, such as the rise and fall of sales numbers over time.
It is also the duty of descriptive analytics to present data accurately and in context. Simply showing the rise of your company’s sales this year might not be enough if, when compared to last year, your sales have dropped significantly.
In such a case, it might be better to plot both the sales of last year and this year on the same graph to show how you are performing compared to the year before.
What is Diagnostic Analytics?
While descriptive analytics seeks to simply present data, diagnostic analytics seeks to deep dive into your data to find the answer to why something happened. For example, why do your sales numbers spike in April? Why are April’s sales for this year lower than last years?
Diagnostic analytics gives insights into why data points have remained static or moved in a certain direction. With diagnostic analytics, sometimes you must look outside the data itself and draw from other sources of data both internally and externally to propose probable correlations.
What is Predictive Analytics?
As the name suggests, predictive analytics focuses on using statistical data to find patterns and forecast the movement of data. In practice, predictive analytics can be used to try to predict problems before they occur or forecast things like sales growth and other business metrics.
From streamlining maintenance schedules to analytics marketing campaigns, predictive analytics can benefit various industries.
A good example of predictive analytics that you are likely familiar with is the recommendation system on Netflix and other streaming websites.
By using data such as your viewing history, your search history, and ratings, Netflix’s system uses an algorithm to predict which shows and movies in their catalogue you would enjoy. Similar systems are used by Amazon to recommend items and Google to choose which ads to show you.
What is Prescriptive Analytics?
Taking predictive analytics one step further, prescriptive analytics seeks to use the actionable insights given by the data. Whereas predictive analytics provides you with the raw data projections, prescriptive analytics seeks to give you various plans of actions based on the data.
Projected results and risks associated with each plan would also be included, so that they can be compared and acted upon.
What is Data Mining?
As the name suggests, data mining is the process of extracting useful information from various forms of unstructured data. This data can be in the form of text, images, audio and more.
The key distinction of unstructured data is that it has not yet been processed, labeled, or formatted for use in data analytics or machine learning algorithms.
A modern example of data mining is sentiment analysis of social media posts to determine brand recognition. This is done by scraping a social media platform, such as Twitter, and collecting a large number of posts. These posts are then examined to learn about the public opinion of your company or brand.
What does Cloud or Cloud-based mean?
A term not exclusive to machine learning, "the cloud" refers to a digital space that exists online. Therefore, when you hear a term such as cloud-based data storage, that refers to a storage system where your data is hosted on remote servers and not stored on premises.
That means the data is not directly held within the hard drive of your computer, but instead on servers that you access through the internet.
What is Machine Learning (ML)?
Machine learning is a field of study that uses algorithms to process and learn from data similar to the way humans do.
It is thanks to machine learning that we have amazing technologies, such as self-driving cars and voice assistants, available to us today. As the machine learning industry grows, more and more people are using ML-based algorithms for data analytics.
What is a Dataset?
A dataset is simply a set of data, often organized into rows and columns. When training a machine learning or data analytics algorithm, datasets are divided into training and testing splits.
The training dataset is used to develop the model and the testing dataset is used to evaluate the model for accuracy.
What is Big Data or Big Data Analytics?
From internet traffic to user behavior, numerous companies both large and small have access to incredibly large, often unstructured, datasets. Big data refers to data analytics methods used to process large datasets often containing hundreds of thousands, if not millions, of rows of data.
…
These were just some of the most common terms you’ll hear in data analytics today. Hopefully, these terms will help you understand more complex articles about data analytics throughout your journey.