Analytics is the systematic process of collecting, processing, and analyzing data to derive meaningful insights,

patterns, and trends. It is used to make informed decisions, solve problems, and predict future outcomes
based on data. Analytics spans various industries and functions, helping organizations to improve efficiency,
understand customer behavior, optimize performance, and drive innovation.
Types of Analytics: -

 Descriptive Analytics
 Diagnostic Analytics
 Predictive Analytics
 Prescriptive Analytics

Descriptive Analytics :
Descriptive analytics deals with past trends data, it basically finds out what has happened in the past, and
based on past data or historic data it predicts the future outcome. One of the main objectives of descriptive
analytics is to look at the trends of past data, summarize it in an innovative way that can be useful for
generating insight.
Example –
Let’s take an example of DMart, we can look at the product’s history and find out which products have been
sold more or which products have large demand by looking at the product sold trends and based on their
analysis we can further make the decision of putting a stock of that item in large quantity for the coming year.
Diagnostic Analytics :
Diagnostic analysis works hand in hand with Descriptive analytics. As descriptive analytics find out what
happened in the past, diagnostic analytics, on the other hand, finds out why did that happen or what
measures were taken at that time, or how frequent it has happened.it basically gives a detailed explanation of
a particular scenario by understanding behavior patterns.
Example –
Let’s take the example of Dmart again. Now if we want to find out why a particular product has a lot of
demand, is it because of their brand or is it because of quality. All this information can easily be identified
using diagnostic analytics.
Predictive Analytics :
Whatever information we have received from descriptive and diagnostic analytics, we can use that
information to predict future data. it basically finds out what is likely to happen in the future. Now when I say
future data doesn’t mean we have become fortune-tellers, by looking at the past trends and behavioral
patterns we are forecasting that it might happen in the future.

Example –
The best example would be Amazon and Netflix recommender system. You might have noticed that whenever
you buy any product from Amazon, on the payment side it shows you a recommendation saying the customer
who purchased this has also purchased this product that recommendation is based on the customer
purchased behavior in the past. By looking at customer past purchase behavior analyst creates an association
between each product and that’s the reason it shows recommendation when you buy any product.
The next example would be Netflix, when you watch any movies or web series on Netflix you can see that
Netflix provide you with a lot of recommended movies or web series, that recommendation is based on past
data or past trends, it identifies which movie or series has gain lot of public interest and based on that it
creates a recommendation

Prescriptive Analytics :
This is an advanced method of Predictive analytics. Now when you predict something or when you start
thinking out of the box you will definitely have a lot of options, and then we get confused as to which option
will actually work. Prescriptive analytics helps to find which is the best option to make it happen or work. As
predictive analytics forecast future data, Prescriptive analytics on the other hand helps to make it happen
whatever we have forecasted. Prescriptive analytics is the highest level of analytics that is used for choosing
the best optimal solution by looking at descriptive, diagnostic, and predictive data.
Example–
The best example would be Google self-driving Car, by looking at the past trends and forecasted data it
identifies when to turn or when to slow down, works much like a human driver.
What is customer lifetime value (CLV)?
Customer lifetime value (CLV) is the total revenue or profit generated by a customer over the entire course of
their relationship with your business. Simply speaking, it's a metric to measure the total amount of money a
software buyer has spent (or is expected to spend) on your products and services throughout their lifetime as
a customer.
The higher the CLV, the more valuable a buyer is to your business, as they would generate more revenue and
are more likely to be loyal. Here’s a quick preview of how to calculate CLV for an individual customer.
Customer lifetime value = customer value x average customer lifespan
Average customer lifespan = (average number of years a customer stays active / number of customers)
Total customer value = (average purchase value x average frequency rate)

 Average purchase value = (total revenue over a set time frame / number of purchases over the same
time frame)
 Average purchase frequency rate = (total number of purchases over a period / number of customers
during that same period)
Some Important Metrics:
Net Promoter Score (NPS):
Definition: A metric that measures customer satisfaction and loyalty by asking: “How likely are you to
recommend our company to a friend or colleague?”
Categories:
Promoters (Score: 9–10): Loyal customers who actively promote the brand.
Passives (Score: 7–8): Neutral customers who may switch to competitors.
Detractors (Score: 0–6): Unsatisfied customers who may discourage others.
Impact:
High NPS correlates with increased customer retention and advocacy.
Helps identify areas of improvement in customer experience.

Customer Satisfaction (CSAT):

Definition: A metric that gauges how happy customers are with a company's products, services, or
interactions.
Common Survey Question: “How would you rate your overall satisfaction with our service?”
Scale:
Typically measured on a scale of 1–5 or 1–10, with higher scores indicating greater satisfaction.
Impact:

 High CSAT scores lead to better retention rates and positive word-of-mouth.

 Identifies areas for improvement in service quality or product offerings.

CLV-to-CAC Ratio:
Definition: A metric comparing Customer Lifetime Value (CLV) to Customer Acquisition Cost (CAC) to evaluate
the profitability of customer acquisition efforts.
Optimal Ratio:

 A ratio of 3:1 is often considered healthy, indicating the CLV is three times the cost of acquiring a
customer.
Impact:

 Helps balance marketing spend and ROI optimization.

Customer Churn refers to the phenomenon where customers stop doing business with a company over a
given period. It is a key metric for organizations as it directly impacts revenue and growth. Churn can occur for
various reasons, such as dissatisfaction with the product or service, better alternatives, or changes in customer
needs.
Churn Rate is often used to measure customer churn and is calculated as:
Churn Rate= (Number of Customers Lost)/(Total Customers at the Start of the Period)×100
HOW TO CALCULATE THE CONFIDENCE, SUPPORT, AND LIFT
What is confidence?
Confidence is a measure of how often a rule is true in the data. It is the ratio of the number of transactions
that contain both the antecedent and the consequent of the rule, to the number of transactions that contain
only the antecedent. For example, if you have a rule that says {bread, butter} => {jam}, the confidence is the
proportion of transactions that have bread, butter, and jam, out of all the transactions that have bread and
butter. A high confidence means that the rule is reliable and consistent.

What is lift?
Lift is a measure of how much more likely the consequent of a rule is to occur when the antecedent is present,
compared to when it is absent. It is the ratio of the confidence of the rule, to the frequency of the consequent
in the whole dataset. For example, if you have a rule that says {bread, butter} => {jam}, the lift is the
confidence of the rule, divided by the proportion of transactions that have jam. A high lift means that the rule
is significant and interesting, and that there is a strong association between the antecedent and the
consequent.

What is Support?
Support is an indication of how frequently the items appear in the data.

More Content Reference Links (Self learning):

How to Calculate the Confidence, Support, and Lift of Association Rules (mishelper.com)

WebFOCUS 8 Technical Library (informationbuilders.com)

What is Support and Confidence in Data Mining? - GeeksforGeeks

Formula:

Example:

Calculation Steps:
Assume there are 100 customers
10 of them bought milk, 8 bought butter and 6 bought both.
bought milk => bought butter
support = P(Milk & Butter) = 6/100 = 0.06
confidence = support/P(Butter) = 0.06/0.08 = 0.75
lift = confidence/P(Milk) = 0.75/0.10 = 7.5