HR ANALYTICS

Faculty : Dr. Mekhala R S

 Unit 1
• Introduction to HR Analytics
• Understanding core concepts of HR Analytics.
Business Intelligence, Business analytics and
its Evolution. Role of Data in HR, Assembling
Data, Describing Data, Visualization. Measures
of Data, Probability and Managing
Uncertainty. HR Analytics: The Third Wave for
HR value creation.
 Origin of analytics
• During the early period of the 20th century,
many companies were taking business decisions
based on 'opinions' rather than decision based
on proper data analysis (which probably acted
as a trigger for Deming's quote). Opinion-based
decision making can be very risky and often
leads to incorrect decisions. One of the primary
objectives of business analytics is to improve the
quality of decision making using data analysis.
 Analytics Overview
"Analytics help organizations to create value by solving problems effectively and assisting in decision making"

• Analytics is a body of knowledge consisting of statistical,

mathematical, and operations research techniques;
artificial intelligence techniques such as machine learning
and deep learning algorithms; data collection and storage;
data management processes such as data extraction,
transformation and loading (ETL);
• and computing and big data technologies such as Hadoop,
Spark, and Hive that create value by developing
actionable items from data. The primary macro-level
objectives of analytics are problem solving and decision
making.
Real world case studies

https://www.aihr.com/blog/
predictive-analytics-human-
resources/
 WHY DO WE NEED ANALYTICS ?
1. It can be used for removing inefficiencies within an
organization.
Many organizations use tools such as Six Sigma to
improve business processes and thus remove
inefficiency within the organization
2. The second objective of analytics is problem solving.
For example, consider a manufacturing company
such as automobile manufacturer who would like to
reduce the inventory cost.
• 3. Third is for Decision Making.

• The primary use of analytics is to help organizations

to take decisions backed by data.

• For example, consider a retail store that has to go for

markdown for apparels sold by them. Many times we
see discounts such as 20%, 40% etc. But the question
is how do you decide right discount for a particular
apparel? It is a complex decision making process
which requires data such as inventory, sell through
rate etc.
• An important objective of analytics is drive innovation. Today we see
several products in the Market such as Amazon Go and Google Maps that
are driven by analytics.

• There was a study published in 2016 in the Journal

MIT Sloan Management Review that only 11% of the
organizations use analytics to drive innovation
• Finally Analytics is used by many companies such as
Google, Amazon, Procter and Gamble as Competitive
Strategy.

• I would like to use the example of the “Monty Hall

Problem” to stress this point.
• Monty Hall Problem is based on a game show in which the
contestants of the game show are shown three doors.
Behind one of the doors is an expensive item (such as a car
or gold); while there are inexpensive items behind the
remaining two doors (such as a goat).
 Instances
• At the beginning of the game, the contestant is asked to choose
one of the doors.
• Assume that the contestant chooses door 3; the game host would
then open one of the remaining two doors. Assume that the
game host opens door 1, which has a goat behind it.
• Now the contestant is given a chance to change his initial choice
(from door 3 to door 2). The problem is whether or not the
contestant should change his/her initial choice.
• Note that the contestant is given an option to switch door
irrespective of the item behind his/her original choice of door.
The problem is based on a famous television show called “Let’s
make a deal” hosted by Monty Hall in 1960s and 1970s.
 Instances
• If Walmart was a country, then its GDP would
be 28th in the world.
• Amazon shipped over 36 million items everyday
during December 2013. Remember they have
service level agreements for delivery which
needs to be met and also they would like to
reduce the cost of delivery. Which will involve
solving problems such as travelling salesman
problem that are difficult problems to solve.
• One of reasons for the increase in use of analytics
is the theory of bounded rationality proposed by
Herbert Simon (1972). According to Herbert
Simon, the increasing complexity of business
problems, the existence of several alternative
solutions, and the limited time available for
decision making demand a highly structured
decision-making process using past data for the
effective management of organizations.
• When a customer of bigbasket logins to their portal they would see
something called Smart Basket. Smart Basket is nothing but a kind of
recommender system which is created based on the customers past
purchase.

• Let us try to understand why bigbasket has created smart basket.

The reason is that many customers place order through their mobile
handsets and it becomes very difficult to scroll through all the
products that they sell at bigbasket. Since this a grocery purchase,
customers order several items in one go. So, if they create a smart
basket, based on customers previous purchase, then it becomes
much more convenient for the customers to place order.
• They also have a feature called “Did You
Forget” that pops up when a customer tries to
check out. This is an important innovation
using analytics that predicts whether the
customer may have forgotten any item which
is common in grocery purchases.
 GAME CHANGERS AND INNOVATORS
• Examples of companies and how they have used analytics
successfully.
• The first company is Google. They developed a page ranking
algorithm using Markov Chain.
• There is an article titled "25 Billion Dollar Eigenvector", authored
by Kurt Bryan and Tanya Liese that discusses how Larry Page and
Sergey Brin developed page ranking algorithm.
• At that time there were many search engines such as altavista,
infoseek etc.
• But Google was much very effective in identifying the most
relevant pages by ranking them using the Page ranking algorithm.
• The second example is Procter and Gamble. They use
analytics as competitive strategy. There is a Harvard
case which talks about how Procter and Gamble is
using analytics as their competitive strategy. Procter
and Gamble, sells large number of products. And,
there's a huge competition for each of the products
sold by Procter and Gamble. Also they have to
compete with private labels or house brand that are
much cheaper than the products sold by P&G. P&G
uses analytics as their competitive strategy.
• The next one is Capital One. In Capital One, they run large number of models
every day. And, one of the things they try to do is who is the most profitable
customer among the list of customers they have.

• The next one is Hewlett Packard. They developed something called flight risk
score to identify which employee is likely to leave. So, if an employee is
important for the organization, they can intervene.

• The last on is Obama's 2012 Presidential Campaign. They developed

something called persuasion modelling. In any kind of election, there'll be a
lot of voters, they may not have decide which way they are going to vote. So,
the question here is "Whether those voters or undecided voters can be
persuaded to vote for a particular candidate?" So, that's what was done by
this particular team, which was developing persuasion modelling.
• There is a German company called Polyphonic HMI. They
developed a model called Hit Songs Signs. Using that
model, they can predict whether a song will be successful
in the market before they release that song in the market.
• The third example is Netflix. And, Netflix developed a
model to predict the ratings given by customers after
watching a movie. So, this algorithm had a root mean
square error of 1%. In fact, few years back Netflix
announced a competition and asked anyone to beat their
algorithm by about 10%.
• Amazon used large number of analytical tools.
It was reported that 35% of sales come from
their product recommendation. There is site
called divorce360.com which predicts success
probability of a marriage. So basically, if you
enter the profile, it'll tell you whether the
marriage will be successful or what is the
probability that the marriage will be
successful.
• Several studies have reported the importance of analytics
in literature. There was an article which was published in
MIT Sloan Management Review in 2010. In this article,
they looked at different companies across different sectors
such as manufacturing, Pharma, Service etc and they
segregated them into high performing companies and low
performing companies. In this article, they claimed that
there is a striking correlation between an organization's
analytics sophistication and its competitive performance.
Basically, the high performing companies were analytically
sophisticated than low performing companies.
 POWER OF ANALYTICS
• Analytics can be classified into descriptive analytics, predictive
analytics, and prescriptive
• analytics.
• In descriptive analytics, we try to find hidden patterns using
descriptive statistics and data
• visualization.
• In predictive analytics, we predict future events such as
customer churn, employee attrition,
• revenue forecasts etc.
• In Prescriptive analytics we arrive at the optimal decision for a
given problem.
 Descriptive Analytics
• Descriptive Analytics describes what
happened in the past using the data,
Predictive Analytics predicts what will happen
in the future and Prescriptive Analytics helps
to decide what action to take
Descriptive analytics is either descriptive
statistics or data visualization.
The first example is from Facebook Relationships
Breakups. In this slide you see a chart on
relationship breakups based on Facebook data.
What we see is two major spikes, one in
December and the other during the spring
break.
• We can only speculate the reasons for spike in relationship
break ups during December.
• Hope it is not a New Year resolution that people would like
to change their partners.
• Probably, too many holidays during December and couples
get to talk to each other, and, probably, they find out that
they are living with a wrong person, so they breakup.
• But what this means to business? The purpose of analytics is
to understand the patterns that exists in data and connect
the dots to understand what it means to business?
 I have listed few possibilities in this slide:

• More traffic to online dating sites in

December/January.
• More demand for relationship lawyers and
counsellors.
• Higher demand for housing in December/January.
• More demand for household items.
• More brand switching (one report claimed that
people change the brand of beer after breakup)
 The third story
• I am starting with the quote. The quote says,
"To understand God's thought, we must study
statistics for these are the measures of his
purpose." You may think that the quote must
have been said by some mathematician or
statistician. Surprisingly, this was a quote by
Florence Nightingale.
• Florence Nightingale prepared a Cox-Comb chart very
similar to a pie chart. The chart is prepared based on the
data from Crimean War, between 1853-1856 to identify
deaths of soldiers during the war and its causes.
• There are three charts in the chart. The first one is the
inner part, where you have the rose color. These are the
soldiers who died because of the wounds sustained in
the war. And, the second portion is a black portion.
These are the deaths because other reasons such as
depression/suicide etc.
• You have a larger ash portion. These are the
deaths due to preventable diseases. Florence
Nightingale took this map to the queen, and
showed the map, and convinced queen that
they have to invest in healthcare otherwise
most of their soldiers will die because of the
preventable diseases. The rest is a history.
• Example of Predictive Analytics include
solution to Problems such as:
• Which product the customer is likely to buy in
his next purchase (recommender system).
• Which customer is likely to default in his/her
loan payment.
• Who is likely to cancel the product that was
ordered through e-commerce portal.
Example of Prescriptive Analytics Problems are:

• What is the optimal product mix?

• What is the optimal route for a delivery truck.
• Best markdown pricing for fashion products.
• Optimal assignment of aircraft to flight.
• How to manage the fleet of vehicles owned by
a company for employee drop and pick up?
• London cholera outbreak in 1854. More than 500 people died during the outbreak. In those
days, people thought the cholera is an airborne disease. During this outbreak, Dr John Snow
collected the residential address of people who died of Cholera and prepared a spot map.
What you see in this slide is the spot map prepared by Dr John Snow. Tick marks in the map
shows the number of deaths at a specific address. In the map You see that tick marks are
concentrated across or around a street called Broad Street. You don't see many tick marks in
other parts of London. So, he thought if it is concentrated in this particular location, there
should be something common among these people who are living in that location. That
common thing was that they were taking water from the same water pump which was
situated in Broad Street. So, he took this map and went to the London municipality and
showed them the map and argues that the cholera is spread through water, requested them
to close the pump. But, the London municipality was not convinced initially because they
showed one entire block where there are lot of people living, but nobody died. In fact, John
Snow was also surprised with that particular building, so he went there to find the truth.
When we went there, he realized that it was a brewery, and there were 70 workers working
in that brewery. And, most of them were drinking beer, not water. In fact, there was another
reason, because they had a separate water pump inside that particular building. So, he found
the answer, he went back to the London municipality, and told them why people in that
building were not dying. Finally, London municipality closed down that pump and the death
stopped. Using a simple spot map, Dr John Snow was able to change the belief from an
airborne disease to waterborne disease.
     

• Which of the following is the process of

analyzing how well an organization acquires
and hence retains talent?
a. Competency Acquisition Analytics
b.      Recruitment Channel Analytics
c.      Capability Analytics
d.      Capacity Analytics
• Ans: a
• __________ are measurements used to track
hiring success and optimize the process of
hiring candidates for an organization.
a. Recruiting Channel
b. Recruiting Metrics
c. Recruiting Process
d. None of the above
Ans: c
• Which type of analytics gain insight from
historical data with reporting, scorecards,
clustering, etc.?
a. Decisive
b. Descriptive
c. Predictive
d. Prescriptive
Ans: b
• The number of employees who left the company
during a specified time period when divided by the
total number of employees that were there at the
start of the time period gives:
A. Employee Churn Rate
B. Employee Turnover Rate
C. Both 1 & 2
D. None of the above
Ans: c
• _____ Analytics is the use of computational and
visualization methods to derive and leverage
insights about shared values and beliefs in
organizations.
a. Cultural
b. People
c. Competency
d. Recruitment
Ans: Cultural
 Thinking corner questions

 What is analytics? Why organizations has suddenly started

focusing on HR Analytics?
 How organizations link Human Resource functions with their
‘strategic drivers’? Name a few companies who have
achieved excellence by linking HR with strategic drivers.
 What is the goal of factor analysis? Give two examples of HR
situations that would call for factor analysis.
 Why employee opinion surveys are important to conduct for
organizations and what are the reasons of using Likert or
Likert type scales for conducting these opinions surveys?
 contn
 A large, global pharmaceutical company was having trouble
with its China market sales force. The problem was two-fold:
the company had issues retaining high-performing
salespeople, and—despite having problems with retention—
the company needed to double its sales force to meet
customer demand and increase market share. They had no
specific retention strategy, and they had little insight with
which to develop one. How will you assist them in developing
an analytics-based predictive retention strategy and solution?
What factors/variables will you consider to collect the relevant
data and what kinds of analytics will you use to provide
feasible solutions?
 contn
 What is HR Analytics? Illustrate with example
the use of HR analytics and its functions.
 What do you understand by term ‘strategic
drivers’? Explain the different strategic drivers
used by companies to achieve organizational
goals.
 Why regression is famous as one of the most
powerful tool in predictive modeling
techniques?
 contn
 Why is it important for organizations to
conduct employee engagement and
satisfaction surveys? How does the
engagement and satisfaction index affect
employee turnover?
 Evidence-based HRM is the order of the day, give
suitable examples to support the statements.
 Employee training involves a lot of costs, how can HR
analytics help in this regard?
 Performance Appraisal is one of the crucial functions
of the HR department and must be done in
alignment with present data records. Comment on it.
 What functions of MS Excel are used to prepare and
clean the data?
 Module 2
.
• Quantitative and Qualitative Dimensions of
HR Planning. Methods and Techniques of HR
Demand Forecasting. Data Base for Manpower
forecasting. Analysis of Labour Market
Behaviour. Analyzing Turnover trends
 Thinking Corner
• Elaborately explain the process of HRP?
• Steps and methods in HR demand forecasting?
 Thinking Corner
• Recruitment Analytics uncover meaningful
patterns of sourcing, selecting and hiring
candidates, elaborate three levels of analytics
to optimize staffing function.
 IMOI APPROACH
An analysis of performance and processing systems that assumes
raw materials (inputs) are transformed by internal system processes
to generate results (output). Applied to human information
processing,

For example, an IPO model assumes that perceptual mechanisms

encode information, which then is transformed by cognitive
processes to result in psychological and behavioural responses.

Similarly, IPO models of group productivity assume that group-level

processes mediate the relationship between individual, group, and
situational input variables and the resulting performance outcomes.
Linking (TA) talent acquisition with (PMS)
performance management system
 Thinking corner questions?
• Define IMOI approach ?
• Explain the process of Linking (TA) talent
acquisition with (PMS) performance
management system with the help of a flow
chart?
• Explain Data analysis levels?