<\/span><\/h3>\n\n\n\nDescriptive Analytics is a kind of data analytics. It looks at old data. It tells us ‘what happened<\/strong>.’ People look at the data they have. They find trends, patterns, and important numbers. This helps them learn things. To show this to others, they use pictures like graphs and charts. <\/p>\n\n\n\nFor example, they can add up money earned, money spent, and profit to see how the business did last quarter.<\/p>\n\n\n\n
<\/span>Diagnostic Analytics<\/strong><\/span><\/h3>\n\n\n\nTo learn ‘why something happened<\/strong>‘ before, businesses use Diagnostic Analytics. Diagnostic Analytics finds the main reason for past things. It digs into data and finds how things connect. People who do this don’t just see ‘what happened.’ They want to know ‘why<\/strong>.’ <\/p>\n\n\n\nAlso, by using old data and checking things out, Diagnostic Analytics helps businesses understand problems. This helps them make better choices. For example, to know why online sales dropped, companies look at website traffic and marketing ads.<\/p>\n\n\n\nTypes of Data Analytics<\/strong><\/figcaption><\/figure>\n\n\n\n<\/span>Prescriptive Analytics<\/strong><\/span><\/h3>\n\n\n\nFirst, we see what happened (Descriptive Analytics). Then, we learn why (Diagnostic Analytics). Next, we must decide ‘what to do<\/strong>‘. This is where Prescriptive Analytics helps. <\/p>\n\n\n\nPrescriptive Analytics gives the best advice for what to do next. It helps people make smart choices with data to get what they want. To do this, it uses tools like models, simulations, and machine learning. <\/p>\n\n\n\n
For example, factories can use it to make the most money. They look at past sales, seasons, and demand to guess how much to make.<\/p>\n\n\n\n
<\/span>Predictive Analytics<\/strong><\/span><\/h3>\n\n\n\nLast, we ask: ‘What will happen next?<\/strong>‘ How can businesses guess future results? Predictive Analytics answers these questions. It’s a key part of types of data analytics. Predictive Analytics looks at old data from many situations. It uses math, stats, and machine learning. <\/p>\n\n\n\nThese tools help businesses make good guesses. Numbers from data are often better than just guessing. So, we talked about all 4 types of data analytics. They help make better choices. They show how to fix a problem with the right data analytics. <\/p>\n\n\n\n
For example, a phone company wants to know who will cancel. They look at bills, money, and customer info to guess who might leave.<\/p>\n\n\n\n
<\/span>Types of Data in Data Analytics:<\/span><\/h2>\n\n\n\nBroadly, there are 2 types of data to analyze, which are given as:<\/p>\n\n\n\n
<\/span>Quantitative Data<\/strong><\/span><\/h3>\n\n\n\nThis type of data is described in the numeric form. <\/p>\n\n\n\n
It has further two types of classifications as:<\/p>\n\n\n\n
<\/span>Discrete Data<\/strong><\/span><\/h4>\n\n\n\nThe data which is in exact or countable form, without having any decimal part.<\/p>\n\n\n\n
Example<\/strong>: Number of Planets, Total Count of Cars, etc.<\/p>\n\n\n\n<\/span>Continuous Data<\/strong><\/span><\/h4>\n\n\n\nThe data which is in real number form, i.e. can be any number within a range.<\/p>\n\n\n\n
Example<\/strong>: Height or Weight of a person.<\/p>\n\n\n\n<\/span>Qualitative Data<\/strong><\/span><\/h3>\n\n\n\nThis type of data is described using qualities, categories or classes, without any numeric form.<\/p>\n\n\n\n
This also further classified into two categories:<\/p>\n\n\n\n
<\/span>Nominal Data<\/strong><\/span><\/h4>\n\n\n\nThe data with no inherent order. Means the order does not matter to decide the ranking. <\/p>\n\n\n\n
Example<\/strong>: Colors of Marbels (red, yellow, orange)<\/p>\n\n\n\n<\/span>Ordinal Data<\/strong><\/span><\/h4>\n\n\n\nThat type of data, where inherent order matters for ranking or preference, is called Ordinal Data.<\/p>\n\n\n\n
Example: Ratings of Customers (very good, good, average, below average, poor).<\/p>\n\n\n
\n
Types of Data<\/strong><\/figcaption><\/figure><\/div>\n\n\n<\/span>Challenges in Implementing Different Types of Analytics<\/span><\/h2>\n\n\n\n<\/span>Data Quality Issues<\/strong><\/span><\/h3>\n\n\n\nFor all 4 types of data analytics\u2014descriptive, diagnostic, predictive, or prescriptive\u2014good data is key. However, it’s a big problem. Data from websites, social media, and other places often has mistakes, missing parts, or is broken. <\/p>\n\n\n\n
Bad data makes the results of data analytics wrong. Also, getting data right away from devices is hard. This hurts predictive and prescriptive analytics. They need fast data to make good choices.<\/p>\n\n\n\n