Data Science is a multi-disciplinary field that make use of mathematical methods, processes, systems, and algorithms to extract knowledge or business intelligence from structured or unstructured data.
Data is everywhere nowadays from social media platforms to banking systems. And for businesses it is quite important to understand the data and gain business intelligence to improve the overall customer experience. The concepts, process, and methods with which the knowledge is extracted from the structured and unstructured data is called Data Science.
Data Science is base for Machine Learning. It is a field of study in which computers/systems gain the capability to learn itself through programming. Machine Learning make use of past data to do predictive analysis and learn itself to predict the future outcomes and take appropriate actions.
Stages of Data Analytics
1. Descriptive Analytics: Inferences from the past data. In this we analyze, what has happened in the past. For example, for each product how much sales were made, how many employees joined in the last quarter and what is their retention rate.
It helps business analysts to find where exactly is the problem.
Tools for descriptive analysis: SAS (It can be used on all stages of analytics), Tableau, SAP, Power BI etc.
Microsoft Excel is also another tool which we can use for data handling, reporting and creating business dashboards. In our data analytics journey, we will first start with MS Excel. After that, we will study SQL and then use Tableau for BI.
Apart from that, I will also be sharing VBA (Visual Basic for Applications) tutorials to write macros at the backend of Excel for tasks automation.
2. Predictive Analysis: In this Analytics stage, we answer business problems – what could happen in the future based on the historical data. The historical data used for predective analysis is obtained from descriptive analysis.
For example, you apply for a credit card. The first business problem for analytical engine is to decide whether you are eligible or not based on multiple parameters.
The second business problem for analytical engine in this case is to decide the credit limit for the eligible person which again depends on different variables like paying capacity, previous payment history, etc. As the value of these variables differ from person to person the credit limit is predicted accordingly.
Without good descriptive analysis, you can’t do good predictive analysis.
3. Prescriptive Analysis: While descriptive analysis answers what has happened in the past, predictive analysis answers what can happen in the future, and in the prescriptive analysis the best outcome is chosen from the set of multiple possible choices.
For example, Google Maps uses prescriptive analysis to show you the optimal route from your source destination to final destination.
Another example is YouTube, which uses predictive analysis to show recommendations. But, it can only show only one video for auto play and for that it uses prescriptive analysis based on various factors like your watch history, search history, etc.
Prescriptive analytics is not possible without predictive analysis.
Road map for Data Science and Machine Learning course
Module 2: MS SQL – RDBMS Concepts and SQL.
Module 3: Tableau – Introduction to Tableau, advance reports, interactive dashboards, etc.
Module 4: MS VBA – Functions, Procedures, Error Handling, etc.
Module 5: R – Data Mining and Modelling.
Module 6: R – Machine Learning
Module 7: Python – Basics, Statistical analysis in Python, etc.
Module 8: Python – Machine Learning using Python with applications.
Subscribe to our mailing list to get email notifications of new updated posts.
So stay tuned for more articles and tutorials related to Data Science and Machine Learning. The frequency would be one post per week or I will increase the number of post as per my schedule. In case, you want to be in touch to ask questions or any other reason, please feel free to connect with me on any of these social media platforms.