HR Analytics People Analytics Using Excel Lecture 2

Welcome to another video of Java Analytics.

This is an action tool.

In the lecture one we discussed about the introduction of

HTML attacks and the importance of each other analytics.

Now we are going to go about this course.

In the lecture two we will be talking about

process of each other analytics.

We should remember when these

you see or you can call it C.

So this is a process of each other analytics from the beginning to the end.

So let's just talk about the steps involved in

analytics process.

As we said, it is the both of these four steps.

C and W.

First, you have to collect data which represents the C.

So we'll talk about what kind of data should we

collect it and how we should be collecting the data for

edge analytics but this is going to be our first time.

In the second step, you need to see the

measurement problems and the measurement issues of the data

that you have already collected.

So this is going to reduce to our second step.

And then we have some kind of decisions on how to

analyze the data.

And obviously after the analysis, when we will reach

to some findings, we need to apply those findings into our

research and making.

So simply speaking, this is step one,

step two, this is C and this is four.

So these are the four steps that we are going to talk about in this video.

Let's start with the first that is the data collection.

Now, usually HR departments have a lot of data

of all the records of employees.

But the problem is, you are not collecting the

HR related data cautiously deliberately for the

analytics.

You might not reach through some good findings.

So it is important that you keep in mind before

collecting the data that you are collecting this data for your

HR analytics and you will be analyzing it and using it for

your decision making.

So one of the major issues that HR departments

is the high quality data.

High quality data means that how do you record this data?

How to collect this data and what kind of data is collected?

And if it is a proof data or it is just

some numbers, collecting and tracking high quality data is

off first by the reports.

Now, the data needs to be

available and people will have been integrated into

reporting systems.

The data should be collected in such a way

that it should be supported by some kind of software

or it should be obtainable.

So let's suppose you are collecting data

in let's say numbers.

And if you have numbers, you can obviously

analyze this specifically and then you can reach some findings.

You can also have some data in words,

but that should be converted into some kind of quantities or something.

Otherwise, there is going to be a qualitative data that might also be very helpful.

But when we talk about analytics, usually we go for

the quantitative data which is in numbers.

Data can come from different sources like

your systems which are already in case you have some kind of

your ISS in which this already data available.

Then you can also look for learning and development systems that you've already

placed. Then you can also collect data using the cloud-based systems

devices and even today's world with a built-in technologies.

So what you're going to do is you're going to

make some Google forms, you might

some health forms are very monkey and your age RIS.

This is how you'll be heading data.

Now what kind of data should we be collecting for our age and analytics?

So there's a variety of data that is available to age

or end to organizations. But these are a few examples of

the data that you can collect which will be useful for your age and

analytics. So implies profiles about the

programs, about the qualification and all of the profiles.

And then about the profiles of the employees for example

who are your high performers, who are your

low performers. We have people are doing good from last

few years which other people were not doing very good from last few

years and which other people were doing very, very low in terms of performance.

Then you can also update about the salary and promotions

of your own employees and the salary and promotion policies of

other companies, maybe your competitors or maybe the

companies operating in the same context or in the same country or

at least in the same industry. You can also

expand analysis of the degree. For example, how it

agrees what owners did you add into summary

and other things. Then how everything data can be collected on

voting which is socialization data can also be collected.

Data related to cleaning, we'll talk about data related to all these things

and then you can also collect data related to engagement of

employees, the retention of employees, one of the important

components is the turnover, population and then

absenteeism and why people are absent and why everything

is happening. You can collect the right

you data and then realize it. The next decision is going to be the

measurement decision. How we are going to measure the data.

So, at the measurement stage, data begins a process of

continuous measurement and comparison of data

with previous data and with other forms of data which

are known as the managers. These are going to be our

very important topics that we will be discussing throughout our

lectures, especially we will have a lot of matrices and

regulations at the end of course.

Each are analytics, usually compares

to data, statistical norms and organizations

standards. For example, if you say that

10% of the turnover is okay, but beyond this

turnover, this is going to be a problem.

So that's going to be our organizations standards.

The process and not rely on a single snapshot of data.

Now the problem is that you can't have a data of one day

or two days or a week and you expect

you're going to get very good findings. You need to have

data related to these several instances from

past because usually you will be doing the

trend analysis. You will be dealing data

for weeks and months and maybe years.

More data that you will have will give you more

related results, more accurate findings.

Data also needs a comparison baseline. So here

one important thing is that organization must set

some kind of comparison baseline.

What is the highest value? What is the lowest value? What

is the average of the things and then you will be able to come up with

some of the findings that you might be applying

for an organization. What is the acceptable

percentage range? What people are

concerned for like two days a month? It is fine for us.

But for some organizations, it might be three days a month.

For example, you can see that we have some

instances like time to hire example how much time

at least you need to hire one employee or

batch of employees, then how much cost

entering in order to recruit one person or

hire one person? How much is the turnover in your organization?

How much is the percentage in your organization?

So you will be talking about these things, but these are a few examples.

Now the analysis part, this is one of the most important slides

when it comes to each analytics. The reason is that you

have to first decide what in of analytics

are you going to talk about and then you will be

applying this and then you will be applying the formula. So starting from

the first one. If you want to know what happened

in the past, then whatever you will be doing, you will be

applying the descriptive analytics because they have

the capacity to describe what happened in the past.

If you want to know why something is happening, then you will be using

an egg not analytics. You will be doing the analysis

of HR data in order to know why something happened

in the past. What happened in the past? And then why

something happened in the past? Then if you want to

decide based on your past and what is most likely to happen

in future, if we have to talk about future,

we will be using the predictive analytics, which is going to

predict what might happen in future. And based on that,

you can always have some strategies to

reduce that loss, increase

something beneficial for you. So predict when

analytics. And then the last one is the

analytics that recommends actions on decisions that

you can take to affect those outcomes. Therefore,

these four types of analytics. And it is important to

consider which type of analytics is going to give

you what kind of results. So you need to understand these terms

and remember them because when you will be applying the

tests and calculations, you have a very, very clear idea

of what kind of analytics are we going to apply.

Then we have the last part, which is known as the application part.

It is a very clear idea that you have

designed to do measurements, and you have

gone through your analysis, and you have

designed to do what you are going to do is that

it is going to give you some findings, and then based on those findings,

you need to take some kind of decisions. So this

application part will give you the decision-making

number based on the analytics that you have performed.

For example, if you have a problem of the

target that your employees are leaving the organization,

you're going to apply the findings that you've got from the

each other analytics. And first you're going to understand

why employees the organization. So once you have this idea

about why, then let's say if you have

findings that you've got training and support

was identified as the contributing factor,

you can improve the training initiatives. So you can

give more training, you can support people who

watch different trainings. The same

way, if you have a problem of

ascentism, then people are

asked from the organization. After the analysis,

you will be understanding the reasons for employees

long-term absences, and as went to enable you

to see any problem with the environment,

any problem with the supervisor, and if

any problem with maybe timings or flexible

timings, so accordingly, you're going to take

some kind of decision, and that's going to then give you

ascentism or less turnover of employees.

This will complete our second lecture in the

next lecture. We will be studying

with humor source planning portion. First we'll try

and understand humor source planning, and obviously we'll be having

some data on pencil, and we'll be in

lines of molars, and we'll be looking at some data,

then how we can perform the human source planning

function. You very much for now. You very much for now.

We will be studying

with humor source planning portion. First, we'll try