 Welcome to the session on classification of analytics. In this session, we are talking about how the analytics is classified, ok. What are the basic schools of thoughts in this one and how these are classified. At the end of this session, you will be learning how to classify the big data analytics, how we can define exactly the analytics 1.0, 2.0, 3.0 in detail. Talking about what exactly big data entails, earlier also we have seen this. Like as the more data is producing, more data is stored, so more data is analyzed. Therefore, as more data is analyzed, the predictions provided are more and the growth of analysis will increase, ok. So, it is a cycle basically of the big data. Talking about the classification of analytics, there are basically two schools of thoughts. The first one is talking about basic analytics, operationalized analytics, advanced analytics, monetized analytics. And the second one is actually showing analytics 1.0, 2.0 and analytics 3.0. Let us see one by one this one. The first school of thought is talking about basic analytics. What exactly basic analytics is? Basic analytics is saying that how the data can be divided, how it can be summarized, aggregated to use for the business insights, how that data can be used for reporting purpose, ok. In this one what happens that historical data is there, earlier data is there, that data is analyzed, and that data is converted into the information, that data may be summarized, aggregated, ok. Data mining algorithms are applied on that on the historical data and the report has to be generated. So, the report may be in the form of a documentation or a visualized data is there, ok. So, that is the basic form of analytics. Next comes operationalized analytics. What is this operationalized analytics? In this one what happens, the enterprises, the business or businesses, organizations are processing the data for their operation in this one. So, the data may be the current data, ok, or the historical data. So, all these one they are processing for getting the decisions in their organization. So, actually the data according to the enterprise needs is operationalized and analyzed for the better decisions in the operationalized analytics. Now, in the advanced analytics what happens that it is about forecasting, ok, for the future. Future predictions are done based on the historical data, ok, based on the predictive analysis. So, this is called as a predictive analysis here. So, predictions are based on the historical data or the data whichever is available, ok, that will be analyzed which is providing some information, some knowledge about what will happen in the future, ok. So, the prediction is done by this one. So, that comes under the advanced analytics part. It is providing the prescriptive modeling also. What this prescriptive modeling is? It is a combination of description, often analysis as well as a prediction also. This comes that is a monetized analytics. What this monetized analytics is? It is actually deriving the business revenue, ok. The business is going on according to this analytics, ok. The major decisions for the business are taken in an organization by this one. It is generating the revenue, ok. So, the analytics is totally monetized here for getting the better business revenues. So, that is what one part of analytics here. So, this is what how the analytics has moved or increased you can see, ok. Basically, it has started with just getting the historical data and then operational analytics is there, then it has advanced by the combination of prediction and prescriptive and finally it has monetized, ok. The second school of thought before that one, let us say pause the video here and we will try to write the answer for what exactly analytics means, how analytics is working or what analytics is doing. Pause the video and you can think on this one. Let us see what it is. Analytics, it is the symmetric computational analysis of data or statistics, ok. Any data is there that is analyzed and we are applying some statistical methods also in that one and why we are using this one? Because whatever the statistical analysis is there that we are using for discovery, interpretation and communication, ok. We are discovering some patterns from that, we are interpreting and we are getting some information from that and we want to communicate that one in a better visualized way, ok. That is what analytics is saying and what analytics is doing? In analytics we are applying data patterns and those data patterns we are using for getting the knowledge, getting the information for the effective better decision making. That is what analytics is saying. Let us move ahead to the second school of thought what it is saying. In the second school of thought for analytics, analytics E is classified as analytics 1.0, 2.0 and 3.0. What are these three? Let us see. Before that just go through this particular diagram what it is saying. See the three sites are there. Inside the historical data it is talking about, inside the current data and foresight the future data, ok. So actually it is moving towards analytics is moving from the historical data to the current data to the future data also, ok. And how it is moving? The analytics is moving. Analytics starts with the description of a descriptive analysis where what happened and when happened, ok, all that information has told. So that is talking about descriptive analytics and then it is moving towards diagnostic analytics. What diagnostic analytics is doing? Why did it happen? Ok, if something has happened we can say that why it is happened? Why did it, why did it happen, ok? That information we are getting in the diagnostic analysis. Next comes the predictive analysis. What predictive analysis is doing? It is providing the prediction. It means that what will happen later? If this thing has happened earlier, ok, if this is the diagnostic thing we have done then automatically it will show that what exactly the future prediction may be, ok. What will happen later? So that information is given by the predictive analysis. Then comes prescriptive analysis. In this prescriptive analysis what will, what it is there exactly? You can see here that how we can make it happen, ok, that is done in the prescriptive analytics. We want to have something in the future and how we can do that one, how we can make it happen that is done by the prescription or a prescriptive analytics because it is a combination of descriptive analysis diagnostic as well as a predictive analytics. A combination of that which is providing the future site. That is about analytics 1.0, 2.0 and 3.0 talking. Let us go ahead with one by one this thing. In analytics 1.0 what will happen that actually it is the introduction of the era of from the beginning of 1950s to till 2009. It is only talking about the descriptive statics. The data is taken from various ERP systems, ERM models or the legacy systems, ok or POS. The data is collected from that and usually that data was from the structured data sources only, ok. Thus data is having some structure, fixed structure and that is usually stored in the enterprise data warehouse or a data mart and internally sourced data is there means the enterprises are generating their own data there and then that will be processed. So, basically it was focusing the relational databases at that time and it is providing the descriptive statistics of particular data, ok. Like analyzing the historical data is there you can say some social media data is there, ok. We want to analyze that thing, collecting that thing, summarizing thing. So, that will be done by this in this analytics 1.0. Next comes the era of analytics 2.0. This is the era from 2005 to 2012 we can say, which is a combination of descriptive statistics as well as a predictive statistics. What predictive statistic was saying that it is talking about the future predictions, ok. Based on the historical data, based on the analysis of the data, based on the description provided through the statistical data, ok, the diagnostic we are doing in that one and then it is providing the predictions on that. So, it is basically using the past data. The data may be unstructured and structured also. So, the data is from the unstructured sources. The data comes from external sources like not generated by the organization. The data may be from outside of the organization also which is generated. So, few applications you can see examples like database applications are there Hadoop clusters, SQL 2, Hadoop environments, we are using all these one in analytics 2.0. Next comes the era of analytics 3.0. What analytics 3.0 is doing? It is introduced in the era of 2012 to till now present, presently we are in analytics 3.0 which is a combination of descriptive statistics, predictive statistics as well as a prescriptive statistic. What it is providing? It is providing the combination of all these one. Again it is using a past data, but it is a blend of big data, ok, combination of analytics of a big data, it is providing the data from the legacy system, ERM, CRM, ok, externally source data, internally source data, everything it is getting and it is providing the better prediction, ok, according to how you will make it happen for a particular future thing. That is done by analytics 3.0. These are my references. Thank you.