Types of Business and Data Analytics

Descriptive Analytics
Diagnostic Analytics
Predictive Analytics
Prescriptive Analytics
Cognitive Analytics

1. Descriptive Analytics: It helps in describing or summarizing what has happened in the

past.
2. Diagnostic Analytics: This focuses on the past performance to ascertain why something
has happened.
3. Predictive Analytics: Using all the past gathered data tells what is likely to happen on a
granular level. The prediction of the possible outcome is made using statistical models and
machine learning techniques.
4. Prescriptive Analytics: It is a type of predictive analytics used to recommend one or more
courses of action on analysing the data.
5. Cognitive Analytics: It brings together several intelligent technologies like artificial
intelligence, machine learning algorithms, deep learning models to mimic the human brain
to derive results from matching human thinking.

Descriptive Analytics
This first type of analytics provides the facts stating what has happened. It is the simplest
type that “allows you to condense big data into smaller, more useful nuggets of
information.” It is the most basic form of analytics performed by more than 90% of
businesses. This is the starting point of any analytics and alone comprises 80% of the
business analytics. The objective is to summarize the results and to understand what is
going on.
Descriptive analytics helps a business learn from its past behaviour and how it will impact
the future. It provides information that helps to understand the performance of the
business on an overall aggregate level. It is also an important step in explaining the current
raw data to the various stakeholders.
This is more like a management information system (MIS), where an MIS gathers data from
multiple online systems, analyses the information, and reports data to aid in management
decision-making. The key techniques used are data aggregation and data mining to
summarize the past data of understanding the data’s underlying behaviour and not for any
predictions.
These are the start of the data analytics value chain and are the most valuable to uncover
any patterns. A simple example of descriptive analytics is to assess credit risk: we can
predict a consumer’s likely financial riskiness by seeing their balance amount against the
credit limit. It is also used to analyse the sales cycle of a store. Also, it can be used to
categorize the customers based on their product preferences, purchase transactions, how
often they purchase. In the context of social media, descriptive analytics offers an overview
of the performance metrics: the total of posts, mentions, followers, comments, page views,
reviews, the average time is taken to respond, and so on.
Examples of descriptive analytics
Many LMS platforms and learning systems offer descriptive analytical reporting with the aim of help
businesses and institutions measure learner performance to ensure that training goals and targets
are met.
The findings from descriptive analytics can quickly identify areas that require improvement -
whether that be improving learner engagement or the effectiveness of course delivery.
Here are some examples of how descriptive analytics is being used in the field of learning analytics:
Tracking course enrolments, course compliance rates,
Recording which learning resources are accessed and how often
Summarizing the number of times, a learner posts in a discussion board
Tracking assignment and assessment grades
Comparing pre-test and post-test assessments
Analysing course completion rates by learner or by course
Collating course survey results
Identifying length of time that learners took to complete a course

Diagnostic Analytics
Diagnostic Analytics is the second type of data analytics. Like descriptive analytics, this also
focuses on the past and ascertains why something has happened. It is also known as root
cause analysis because it looks deeper to understand the events’ root cause. It allows us to
isolate the patterns to identify these patterns’ source and the factors that affect the
business. The diagnostic analytics helps to understand, for instance, why there has been a
sudden surge or decrease in sales.
This type also helps detect the anomalies and determine the causal relationship for the
cause and effect present in the data. It is characterized by discovering data, data mining,
and correlations. Some of the techniques employed at this stage are feature importance,
principal component analysis, sensitivity analysis, conjoint analysis. To analysis, it mostly
uses probabilities, likelihoods, and the distribution of outcomes.
Diagnostic analytics for social media campaigns can refine the descriptive analytics stage
data into one view to see what did or did not work in the past campaigns. Retailers can
break down the sales and gross profit to various products and subcategories to understand
where and why they missed the overall profit margins. Another use case of diagnostic
analytics is in healthcare. One can identify the impact of medicines on the patients and can
be used to study the effects of before and after treatment.
This type only uncovers and provides the casual relationship, and it cannot provide any
actionable insights, hence has limitations. That’s why the next two types of analytics are
important.

1. Examining Market Demand

One use case of diagnostic analytics is determining the reasons behind product demand.
For example, take meal kit subscription company HelloFresh. The company gathers millions of data
points from global users, including information about geographic location, disclosed demographic
data, meal type, flavour preferences, and typical order cadence and timing.
HelloFresh’s team uses this data to identify relationships between trends in customer attributes and
behaviour. As a hypothetical example, imagine the HelloFresh team identifies a spike in fish-based
recipe orders. After conducting diagnostic analysis, they find that the attributes most highly correlated
with ordering fish recipes are identifying as female and living in the northeastern United States.
From there, the team could conduct market research with that specific demographic to learn more
about the demand for fish recipes. Was it caused by a recent scientific study touting the health
benefits of fish for women? Perhaps people who live in the northeastern United States have a refined
palate for seafood because they live relatively close to the Atlantic Ocean. Their reasoning could
provide impactful insights to HelloFresh.
Dipping into the other types of analytics, the team could also consider whether the trend is expected
to continue (predictive analytics) and if it’s worth the effort and money to create more fish-based
recipes to cater to this audience’s preference (prescriptive analytics).

2. Explaining Customer Behaviour

For companies that collect customer data, diagnostic analytics is the key to understanding why
customers do what they do. These insights can be used to improve products and user experience
(UX), reposition brand messaging, and ensure product-audience fit.
Continuing with the HelloFresh example, consider the value of customer retention to the company,
which operates on a subscription model. Keeping customers is more cost-effective than obtaining new
ones, so the HelloFresh uses diagnostic analytics to determine why departing customers choose to
cancel subscriptions.
During the cancellation process, departing customers must provide their reason for cancelling.
Options range from “doesn’t fit my budget” to “doesn’t fit my schedule or dietary needs,” and there’s
also an option to write in an answer. By gathering this data, HelloFresh can analyse the most cited
reasons for losing customers among specific regions and demographics and use diagnostic analytics
to answer the question, “Why are people cancelling their subscriptions?”
These insights can help improve HelloFresh’s product and user experience to avoid losing more
customers to those reasons.

3. Identifying Technology Issues

One example of diagnostic analytics that requires using a software program or proprietary algorithm is
running tests to determine the cause of a technology issue. This is often referred to as “running
diagnostics” and may be something you’ve done before when experiencing computer difficulty.
Some of these algorithms are constantly at work in the background of your machine, while others
need to be initiated by a human. One type of diagnostic test you may be familiar with is solution-based
diagnostics, which detects and flags symptoms of known issues and conducts a scan to determine the
root cause. This can allow you to address the issue and escalate it if the cause is serious.

4. Improving Company Culture

Diagnostic analytics can also be leveraged to improve internal company culture. Human resource
departments can gather information about employees’ sense of physical and psychological safety,
issues they care about, and qualities and skills that make someone successful and happy. Many of
these insights come from running internal, anonymous surveys and conducting exit interviews to
identify factors that contributed to employees’ desire to stay or leave.
Gathering information about employees’ thoughts and feelings allows you to analyse the data and
determine how areas like company culture and benefits could be improved. This can include anything
from wishing the company made more corporate social responsibility (CSR) contributions to feeling
discriminated against at work. In these cases, the data presents a case for allocating more resources
to CSR and diversity, equity, inclusion, and belonging efforts.
Insights from surveys and interviews can also enable hiring managers to determine which qualities
and skills make someone successful at your company or on your specific team, and thus help attract
and hire better candidates for open roles.
Diagnostic analytics can help boost employee happiness, safety, and retention, as well as lead to
more effective hiring processes.

Predictive Analysis
Predictive analytics uses the gathered data and descriptive and diagnostic analytics results
to tell what is likely to happen in the future on a granular level. This is where the earlier
steps’ insights can be used into actionable insights for decision-making. Its use involves
forecasting the future, predicting the market trends, changing customer behaviours, and
analysing competitors to optimize and build strategies to maximize the business results.
The predictions are made by analysing the past data, detecting patterns, casual relationships
in the data, and then extrapolating them in the future. For instance, a bank to predict which
customer is likely to default will need all the past data about which customers have
defaulted to predict. The inferential statistics, training algorithms for regression,
classification, and segmentation come under this type of business analytics. It uses the
techniques to segment the data into groups, apply clustering methods, heuristic rules,
decision trees to project future outcomes.
The predictive analysis can also be used to generate, test, and evaluate hypotheses. It is
useful to understand whether a set of features are explaining or predicting other features.
For example, it can validate a person’s hypothesis inhibiting from a certain region, age
group, gender defaults in its credit card payments. This is especially useful when some of
the features are actions determined by the business decision-makers. One of the
applications of prescriptive analysis is sentiment analysis.
Predictive analytics is extensively used in every industry: finance, healthcare, social media,
sports, energy, manufacturing. One of the most frequent applications is in retail, where the
retailers are always using predictive analytics to predict and improve their sales positions.
Amazon’s recommendation engines are a classic example where on making one purchase,
the engine shows the list of other similar items that the buyers have purchased.

Example of Predictive
Health
Google Flu Trends (GFT) was an early attempt to predict flu patterns in the population. However, the data collected was
not ideal and thus the predictions were also incorrect. We are now seeing PA being used to predict epidemics, when a
patient needs behavioural health care, and why patients need to be readmitted.
Sports
One of the most interesting examples of companies using predictive analytics is Bing Predicts which is a system by
Microsoft. It has consistently scored in the high 90s percentage of predicting U.S. House and Senate races, is in the 80
percentile American Idol, and was 100% accurate in the predictions of the 2014 World Cup. Bing Predicts uses statistics and
social media sentiment when making its predictions.
Financial modelling
One of the most common applications of A in finance is its use in credit ratings to determine if a loan should be approved.
A good automated model will be able to predict if a loan is high-risk or not in a matter of a few minutes. PA is also applied
in the optimization of business strategy, revenue generation, resource optimization, and sales generation.
Retail
PA is most widely used in the retail industry. One of the best examples of predictive analytics in business is the
recommendation list on Amazon’s website. It uses the data of customer behaviour and past transactions to determine
which products will most likely result in a sale.
Social Media
The sheer data available on social media is made simpler to comprehend with the use of examples of predictive analytics in
marketing. Content posted by customers and potential buyers is combed through to inform business decisions.

Prescriptive Analytics
Building on predictive analytics, prescriptive analysis is the next step that helps in exploiting
the future. It essentially tells the business what should be done. Using simulation and
optimization, it advises on the possible outcomes and suggests actions that can maximize
the key business metrics. The focus here is on how to make it happen. 
It can be defined as a business optimization data analytics that provides insights on “what
should a business do” to solve a problem. It explores several possible outcomes and
suggests actions depending on the results of descriptive, diagnostic, and predictive analytics
of the data. The prescriptive analysis uses a feedback system that constantly learns, updates
the relationship between the action and the results. 
Examples of Prescriptive Analytics in Healthcare
In 2018, the healthcare industry was worth $8.45 trillion. It’s no doubt grown since then and will keep growing
still
Healthcare is one of the markets most ripe for an analytics revolution. But like any multi-trillion-dollar industry,
healthcare can be a bit sluggish when it comes to technological evolution.
One of the reasons healthcare is so well-suited for predictive analytics is because of the sheer amount of
collected data.
Think about all the electronic healthcare equipment like EKG machines, blood pressure monitors, and digital
thermometers. All these things have the potential to connect to a closed intranet and send information.
Robust prescriptive models could prevent disease and even save lives. But alas, that’s still a way into the
future. For now, we have to start with baby steps.
Consider THIS EXAMPLE from Sajan Kuttappa, a product marketing manager at IBM.
A health insurance company analyses its data and finds that many of its diabetic patients also suffer from
retinopathy.
With this information, the provider can now use predictive analytics to get an idea of how many more
ophthalmology claims it might receive during the next year.
Then, using prescriptive analytics, the company can look at scenarios where the reimbursement costs for
ophthalmology increase, decrease or hold steady.
The business can make informed decisions about how to proceed in a cost-effective way that also serves its
customers.
In the actual hospital, prescriptive analytics can play a vital role as well.
Consider how much data hospitals collect in the following categories alone:
Patients
Treatments
Appointments
Surgeries
Radiologic techniques
Now imagine if that data got fed into a prescriptive analytics model. The insights could help ensure the proper
staffing of hospitals and help triage patients.
Utilizing data rather than gut feelings can save costs on everything from medical supplies to transport fees to
food budgets.
Examples of Prescriptive Analytics in Sales
It should come as no surprise that one area where prescriptive analytics can really have an impact is sales.
Taking all your descriptive, diagnostic, and predictive data and then analysing it with a prescriptive
methodology can impact every step of the sales process.
Consider the following real-world applications of prescriptive analysis:
Maximizing first-contact success rates
Sending the perfect piece of collateral that’s had the most historical success with this demographic
Driving’s customers to the bottom of the sales funnel to complete their transactions
It can even help your sales team become more effective at their job.
Prescriptive analytics can show a sales team member where all their customers are in the purchasing process.
By analysing a wide range of factors, it can then help them rank their leads.
They can focus first on who’s most likely to complete the sale, then address the “fence-sitting” prospects.
It can even offer up suggestions for how to keep specific customers moving through the funnel.
Sales managers can also examine prescriptive data on each sales rep to see where they tend to lose a
customer in the buyer’s journey.
If a rep is losing leads early or in the demo phase, there’s an issue with how they’re opening with clients or
showcasing the product.
If they’re losing sales at the bottom of the funnel, prescriptive analytics can offer a different approach to get
the employee back on track.
Armed with this information, the manager can work with the sales rep on their specific issues to help them
better reach quotas and goals.
Prescriptive analysis should be a goal of every major sales department going forward. This level of insight into
customer and sales rep behaviour is a game-changer.
Prescriptive analytics in sales is our area of expertise. Check out this interview with Accent CEO Pete McChrystal
and Subject Matter Expert Nicholas Scahill as they answer questions about the state of Sales AI and how it’s
shaping the Sales Enablement industry.
It does not predict one possible future but rather multiple future outcomes. It is an advanced analytics concept
based on optimization and simulation. Optimization helps understand how to achieve the best outcome and
identify the data uncertainties to make better decisions. The other approach of prescriptive analytics is a
simulation in which all the key performance areas are combined to design the correct metric goals. This
ensures whether the key performance metrics are included in the solution.  
The prescriptive analysis is performed when scenario analysis simulates the future under various sets of
assumptions and combines it with different optimization techniques.  It uses statistical models and machine
learning algorithms to estimate the probabilities, optimizing and recommending actions. A prescriptive model
can recommend the best course of action for any pre-specified outcome as it can predict the possible results
based on a different choice of action. Waymo, Google’s self-driving car, is an example of prescriptive analytics.
Recommendation engines are a use case of prescriptive analysis.
Prescriptive analytics can be applied to almost any industry where the population is to be targeted or grouped.
It also has its applications in marketing, financial markets, and the transportation industry. In social media,
grouping the customers under one bucket based on their characteristics can use prescriptive analytics to
optimize the offering to each group. Similarly, it can be applied in the transportation sector to save time and
resources by optimizing the best routes. In the financial markets, the researchers heavily rely on statistical
modelling to maximize the returns and manage risk and profitability.

Cognitive Analytics
This is the most advanced type of business analytics that applies human intelligence to
certain tasks by combining many technologies such as artificial intelligence, semantics,
machine, and deep learning algorithms. The goal is to understand and mimic how a human
brain makes a decision and comes with a system or computer that does the same. Some of
the tasks that can be performed using cognitive analytics are chatbots, virtual assistants,
recognizing objects in an image, and segmentation of those images.
Cognitive Analytics works by searching the entire available “knowledge base” to locate real-
time data. It is highly dependent upon and often combines artificial intelligence techniques,
machine learning, deep learning, neural networks, and semantics. It mimics the human
brain to study and learn from the available data to extract actionable insights hidden behind
data patterns. It collects and makes real-time data sources such as text, images, audio, and
video available to these analytics tools for decision-making.
 Netflix might recommend movies based on a user’s past preferences.
 If you purchase a dog toy on Amazon, you’ll suddenly see a bunch of related products for your pooch.
 Liked a Facebook post showing a remodelling project? You can expect to see home improvement content
showing up in your news feed.
1. Vantage Point AI
Industry: Finance
Challenge: Providing accurate, fact-based investment recommendations
Choosing a well-performing stock has traditionally been a guessing game for many investors. With the help of
machine learning and artificial intelligence, investors can feel more confident in their investment decisions.
Vantagepoint AI was recognized for its predictive artificial intelligence trading software used by over 29,000
traders around the world and named the Best A.I.-Powered Trade Software Solutions Provider.
Vantagepoint is considered a leader in investment trading software research and development and has been
shown to forecast stocks in twelve U.S. sectors including energy, financial, healthcare and technology as well as
stocks around the world. This tool can forecast stocks, futures, Forex and ETFs with accuracy of up to 87.4%.
According to Vantagepoint’s website, its patented Neural Network processes predict changes in market trend
direction up to three days in advance, enabling traders to get in and out of trades at optimal times with
confidence.

2. Welltok
Industry: Healthcare
Challenge: Providing access to reliable, up-to-date health and benefits information
If erroneous health information on the internet weren’t prevalent enough, new — and often conflicting — health
research is being published every day. The pandemic has only increased the number of bogus health claims and
misinformation. These realities make it difficult for many people to find accurate answers to their medical
questions.
Welltok offers a cognitive-powered tool called HarmonixTM that can instantly process vast volumes of data to
answer questions and make intelligent, personalized recommendations. Welltok offers this service to health
insurers, providers and similar organizations as a way to help their subscribers and patients improve their overall
health in a truly personalized way.
Welltok was recognized as the 2021 Best IoT Healthcare Platform in part for its ability to predict with up to
90% accuracy people's needs and their likelihood to take action, and engage them with integrated multi-channel
outreach to maximize results.

Ques. What is the difference between cognitive analytics, predictive and prescriptive
analytics?
Cognitive Analytics applies human-like intelligence to certain tasks. It combines
technologies, such as semantics, artificial intelligence algorithms, deep learning, and
machine learning, to learn from the interactions with data and humans.  On the other hand,
predictive analytics tells what is likely to happen in the future, and prescriptive analysis tells
what action could be taken.