Skip to main content

The 4 Types of Data Analytics

 

Analysis, the key of success

Analysis of data is the key to become successful as human, and even better, to succeed on running a business. When data are used effectively in an efficient way you can get fast and clear observations on the past performance of your life and your business, and then to make better decisions for the future. There are million ways that the data analytics can support you, in any level of your business in order to achieve any target of your choice.

However, to succeed your goals, you need to know the four types of data analysis that are commonly used in every business in every industry. Every category has its own target and they are connected to each other. What's even more, every category is an extension of the other so you need to have a consolidated view and understanding of each category to find the seeking outcome. As you can see at the below graph demonstrates the complexity of each category and added-value contribution. At the same time you can see that the level of difficulty is increasing as well as the knowledge that you need to have in order to  implement them.




Let's introduce with few simple words each one of the categories and describe how and where this can be used of your own benefit.

Descriptive Analysis

People all around the world when they are starting an analysis, the first thing that they are asking is the what? So, the answer to the question "what happened?" is the first priority for every analyst to get clear page of view about the problem in order to understand everything. Remember that you cannot analyze and improve anything without knowing exactly what it happened.

Now, where can we use it in our business? Basically it can be used in every single thing that concerns every manager who own a project. The identification of the key performance indicators of-course. In this way the performance of your business can be described within specific benchmarks and then to be able to go deeper in to the problem.

Diagnostic Analysis

As mentioned above, these categories are linked, so after the answering of the above question you need to learn why it was happened exactly. In order to be able to make decisions you need to learn everything about the specific event. So,  "why it was happened?" is the second question that need to be answered.

This type of analysis is focused on a starting point of the past until the ending point of the specific event. By implementing it, basically,  you are trying understand the flow of the event and the methodology that has followed. This is commonly used in every business or in real life. We are trying to understand why something goes very wrong or very well to impove it accordingly and identify where we need to focus.

Companies are using this analysis to investigate a problem by diving deeper into their data. Since we have the data, it is up to the analyst to simulate this information and understand the path data follows to get to the resulted outcome.

Predicitive Analysis

The next Analysis, which it is the most favourite to me, is to attempt to answer the question "what is likely to happen?". Basically, after the processing of the past data we can use the outcome to make predictions for the future.

Logical predictions can be resulted by processing the past data usimg statistical methods. The statistical modeling, which requires the knowledge of machine learning algorithms most of the times, requires high level of technology and an expert human on this field to forecast. It is significant to mentioned that, these predictions are only estimates of what it will happen. No one can be sure 100% about the future.On top of this the accuracy of the prediction depends on the quality of the data and the algorithm that it will be used.

In business , the above analysis is used to predict prices, classify clients into groups, find their risk assessment and pretty much everywhere that a business needs to be successful at the future.Because of the high technology involved and knowledge that is needed for this analysis, a lot of companies afraid to invest on it due to the high expenses that comes with it.

Prescriptive Analysis

Finally, we have the type of analysis that few organizations have a special equipment to support it. It is considered as the most sought analysis in the market and everyone tries to understand it and gain the appropriate knowledge to implement it. By combining the previous types of analysis, we are attempting to answer the question "How it should be accomplished?". It's a crucial question, as it needs a decision maker, human or system, to decide the course of actions in order to get the desired outcome.

Artificial Intelligence is a perfect example when we are trying to answer the above mentioned question.  The AI systems are capable to take the information and use this info to take decisions. The design of mentioned AI system needs to be in a proper way that can take these decisions and putting them into action. As a result, the engagement of human on this clever systems it is not a necessity due to the daily optimization of the decisions.

Most of the big companies on the market like Facebook, are utilizing this kind of analysis and try to improve it every day, in order to create an autonomous environment, as a result, the less needing of manpower and more computer power.

Conclusion  

All the types of analysis have their fundamental role to solve problems. Each one of them is serving its own purpose but cannot be avoided or ignored in a succesfull orginisation.By moving from the low level to top level of the graph, the knowledge that is needed, as well as the requirments, are increasing dramatically, so before developing any kind of the above types of analysis, find the problem and then take the correct decisions for the benefit of your company.

Comments

Popular posts from this blog

Data Analytics and Science, can they coexist or not?

The high level technology has been expanded Technological achievements have impressed everyone the last three decades, especially when it comes to the storing in big electronic storages data without the need of paper and ink. This was the result of creating unmistakable databases of data, without the sloppy human hand and pointless effort. In this high level storages, the necessity of the data analysis field, has been erected. Industries of every field have evolved as a result to have the need of having someone to analyze their data to create a clear view of where they stand and where they are heading.  By manipulating the enormous and complicated structured and unstructured data are stored in the mentioned electronic views such as databases and cloud, different kind of techniques and methodologies have been developed to create a peaceful environment for all the analyst. Analysts in some cases are called "The story tellers" because are able from unrelated data to create meani...

The role of Data Scientist in 2022

  As it was mentioned in previous articles, data analysis is used for data processing and data manipulation which are the processes of changing or altering data in order to organize them and make them more understandable.   The 4 types of analysis  have been briefly analyzed but in order to be able to use them, you will need programming knowledge. Due to the enormous number of structured and unstructured data, it is necessary to process them using advance technology to derive meanigful information. The programming languages and other BI tools, are the most important factors to accomplish the data analysis. So, every data scientist or analyst will need to know abouth the aforementioned. What are they assuming about data scientist role? One of the analysis types is the predictive analysis, which involves the implementation and usage of machine learning algorithms to predict or classify the data. Regarding the role description, what is being advertised and what a d...