Brief Introduction to Data Science

In today’s information overloaded world, the amount of data being collected is increasing drastically. Retailers collect shopping habits of customers, websites collect email addresses of visitors, social media collects images, video and audio data of users, builders collect living habits, banks collect demographic details, mobile devices collect location information of users etc. The list does not end here. It goes on and on. Data is the core of any business and organisations that fail in using their data in a smart way is not going to survive in this competitive world. So, organisations are finding new methods to use the data they have in the best possible way.
 
In the past, organisations used to employ statisticians or data analysts to extract required information from the available data. But the volume and variety of data make manual analysis literally impossible. Moreover, technology advancements in the area of computers made it possible to have more broader, deeper, quicker and accurate data analysis.
 
Most of the time, knowledge is buried within data. In other words, answers to many vital questions are buried inside messy data. Data science refers to collection, preparation, analysis, visualisation, and management of large collection of data in order to extract insights from messy data. In fact, data science is much more than simply analysing data.
 
Data science uses a number of methods and theories emerged from different areas such as mathematics, statistics, databases, machine learning, artificial intelligence, data mining, visualisation and computer programming. Businesses and organisations can identify patterns and regularities in data with the help of data science and such knowledge can be used to make better decisions that improve the business in a multitude of ways. In short, data science involves principles, processes and techniques to analyse huge amounts of data in order to extract knowledge from them.
 
The major three processes involved in data science are data acquisition, data analysis and data archiving. Data acquisition focuses on how the data are collected and represented before analysis and presentation. Data analysis is the main process in data science which involves summarisation of data to make inferences and presentation of data in the form of graphs, tables or even animations. The final process is data archiving where the data is preserved in a highly reusable form.
 
The processes involved in data science are very difficult to complete because of many reasons. The main reason is the heterogeneous nature of data. We cannot include all the available data in a database. The data could be audio, video, text files, and even bits and pieces of information. So, preparing the data for the analysis process itself is a real headache. Moreover, data science requires costly analytics tools and high skills and expertise to use those tools properly. In short, data science is really complex than we think.
 
Data science is most applied in the area of marketing that includes targeted marketing, online advertising and recommendations for cross-selling. It is also found to do wonders in the area of customer relationship management. Insights extracted using data science help to analyse customer behaviour and hence to maximise expected customer value. The banking industry uses data science for fraud detection, credit scoring and workforce management. Major retailers make use of data science throughout their businesses, from marketing to supply-chain management.