Shrihari Mundada 18 min

Is your Installed Base data a Mess?

Clean and unify Installed Base data with Entytle

You Might Also Like

0:00

Let me go ahead and introduce our speaker of the day.

0:04

We have Shri Moondata, who has worked with in titles

0:07

for the past eight years.

0:10

He takes care of the entire data and DevOps infrastructure

0:13

for in title.

0:14

He has been instrumental in building

0:16

an in-salt-based data studio focused on industrial data

0:20

workflows, which he's going to go ahead and jump into

0:22

with that being said, Shri, all.

0:24

But you take it away.

0:28

Thanks a lot for the introduction, Colin.

0:30

Hello, everyone.

0:31

And thank you for joining our webinar today.

0:33

I'm excited to talk to you about a common challenge

0:36

based by industrial OEMs, which is managing the install

0:40

based data effectively.

0:43

Most of you would agree to this that this is a comprehensive

0:47

process.

0:48

And with the next few minutes, I'd like to shed light on,

0:51

how do we do it differently and repeatedly, and at a larger

0:54

scale at the end of the title?

0:56

So let's start with the scenario, which many of you

1:00

might be familiar with.

1:01

Your install based data, as you see in this slide,

1:04

would be scattered across various functional systems,

1:06

like CRM systems, ERP, FSM, different spreadsheets,

1:11

or e-commerce tools, legacy systems, and so on.

1:14

And each of the systems may hold valuable information,

1:17

but accessing and unifying this data can be a daunting task.

1:21

So it's like having all the pieces of the puzzle,

1:24

but not being able to see the complete picture.

1:26

And this is what we see across every single prospect

1:30

or customer that we talk to.

1:32

On top of that, the data here would be often messy,

1:35

inconsistent formats, duplicate entries, incomplete records.

1:39

It really makes it difficult to gain accurate insights

1:42

on to the data.

1:43

It becomes a big hindrance and leads to missed revenue

1:47

opportunities.

1:49

And this problem gets further compounded by the data silos.

1:52

And it's not that companies do not

1:55

make investments in this area, but thing

1:57

is the lack of a comprehensive process

2:01

around this data-fitting cleaning notification

2:05

leads to eventually get another silo.

2:09

So what's the solution?

2:11

And where does the entire comment to picture?

2:13

So what the entire list has done is

2:15

we have created a clean and unified process

2:19

that does the data cleaning enrichment analysis

2:24

on your IB data, which keeps your IB objects at the center.

2:30

So if we look at this data journey,

2:32

so here what we are striving is to transform your raw data

2:37

into actionable insights through the entire installation

2:40

platform.

2:41

So we begin by gathering the relevant data

2:43

from different systems.

2:45

Then we move to data exploration, where

2:47

we do a lot of everything on the data quality

2:50

and the data cleaning part of it, before feeding it

2:53

to analytics pipeline, where we have built certain custom

2:56

purpose-built models centered around the IB data.

3:01

And only when we have validated those results,

3:06

practice, set them, we push it to the final destination,

3:11

which are basically actionable intelligence, which

3:15

are accessed by our customers leading

3:18

into more new opportunities for them.

3:21

Having said that, the most crucial aspect in this journey

3:24

is the data quality, as it lays the foundation

3:29

for accurate analysis and generate

3:32

reliable insights in your IB data journey.

3:35

So we'll just deep dive into the data quality piece

3:39

because it has to be really comprehensive.

3:43

So if you take a step back and understand

3:45

what are the primary objects around the IB data?

3:48

So they could be transactions, equipments,

3:52

item master, bill of materials, service data, service

3:56

contact data, warrant these location masters,

3:58

and all of these data in real life

4:00

is scattered across different systems.

4:02

So the first thing is it should be cleaned and unified

4:05

and also enriched further so that you can

4:09

trick this into a high quality install base.

4:12

And during this process, it's also

4:14

important to have proper data governance and security

4:16

practices because it's important to ensure

4:19

integrity and protection of data.

4:22

But having said that, it's a very recent and done,

4:25

basically.

4:26

As you can see in this slide, cleaning and stitching

4:29

this install base data is a comprehensive process,

4:32

but it requires a lot of investment,

4:34

diverse skillsets, multiple tools, which

4:37

is really a time consuming and expensive thing to do.

4:40

So at the entitled, we have built something called

4:43

as a part of the installation platform.

4:48

We have built something called as the entire install base

4:50

data studio, which unifies all the data from all of your

4:54

different systems into a single cohesive system.

4:58

So this ensures that we achieve high quality data,

5:03

focused around your IB use cases, and on that high quality

5:08

data, we generate C60 degree analysis

5:13

like the parts of your training, equipment

5:15

training services, revenue training, identify the health

5:17

of your customers, both at a macro and micro level,

5:20

and make specific predictions and prescriptions

5:24

around equipments, opportunities, parts, opportunities,

5:28

and so on.

5:29

So at a high level, this is what our approach is.

5:36

What I do is I directly jump into our product demo

5:39

because the proof of the pudding is in the eating,

5:42

where I would actually show, what is it that entire install

5:45

base data studio has to offer and how do we do it?

5:47

As you can see here, into the IB data studio,

5:54

we have different workspaces for different personnel.

5:56

One is data prep workspace, where we do all the data

6:00

profiling, stitching, and cleaning, and stuff.

6:03

There is the analytic and the setup, basically,

6:06

the meta data management.

6:08

In the analytics, we have descriptive, predictive,

6:10

and predictive opportunities on the clean and unified IB data

6:14

that would have done into the data prep workspace.

6:16

Once we jump into the data prep workspace,

6:18

you would see a lot of services.

6:20

All of them are like self explanatory.

6:21

So data prep is where you prep all the data,

6:24

data loader, and data load is where we ingest this data

6:28

into our target systems.

6:30

And deduplication is where we deduplicate locations,

6:34

which is a common identifier across all different systems

6:38

that we have spoken about earlier.

6:41

So on the data acquisition side, you can upload file

6:45

from your local machine, or you can import directly

6:47

from your databases, import directly from snowflake.

6:50

And once you have imported data, we run several jobs

6:54

to profile that data.

6:56

So if I jump into one of the jobs, what you can see here

6:59

is a data distribution, which helps in identifying outliers,

7:04

missing values, the patterns in your data.

7:07

Or example, if I look at the report of this particular data

7:10

center that I have, it has roughly 150,000 records.

7:14

And 30% of the data is missing.

7:18

Now, if you look at this, you have different attributes,

7:21

cardinality, or different columns, which denotes

7:24

what are the, what is the, what how many number of records

7:28

in your data are distinct?

7:29

It will buy the book, why was it your book,

7:32

so you would identify any outliers in your data.

7:35

So doing this in the initial phase helps you really identify,

7:39

helps you identify how does my data quality look like?

7:42

Is this because if take a classic case where your data

7:48

may be lying into two to three different systems,

7:49

we could unify that and bring all of that data together.

7:52

And this gives you a unified picture of your data

7:55

distribution.

7:55

And then you can take a call on how do you improve the quality

7:58

of this data?

7:59

And if it is good, you move ahead, or if not,

8:04

you can perform several elementary and complex data

8:08

operations.

8:09

Some of them are merging a column,

8:12

was splitting a column, deleting it, renaming it

8:14

for better readability.

8:16

There are no code-local operations like find and replace,

8:19

find and replace by regular expressions.

8:21

You can just find by certain pattern and then replace it

8:24

by a specific value.

8:27

There are SQL type joins, where you can do left, right,

8:31

inner join on your data.

8:34

Then so I can choose a data set and do a left, right, inner join

8:39

also out a join with any other data set.

8:41

There are no code operations like create new column of type

8:44

string number, date, Boolean.

8:46

And you can perform various operations.

8:48

So if column A is empty and column B is not empty.

8:51

So different kind of no code things.

8:54

You can define a uniqueness criteria on your data.

8:58

You can say that a combination of n number of columns defines

9:02

my record as unique.

9:04

And what it is, it would drop duplicates.

9:07

That's how you keep unique records.

9:10

Then there are other operations like SQL type group

9:13

by or SQL type ranking functions, where you can group

9:15

by certain things and then you can use certain functions.

9:19

One of the use cases is you would have

9:22

caught some initial set of data from your system.

9:24

Now you want to apply an additional data to this.

9:26

So you can union it pattern matching

9:30

barricular expressions.

9:31

So you can count and extract matches

9:33

by certain regular expressions.

9:35

And the best part is whatever you do,

9:37

you can put this as a part of the recipe so that the next time

9:42

when you get similar data, you can rerun the same recipe step

9:47

that you had written earlier.

9:50

And what you are seeing here is something

9:53

called a ribic continuum, basically, which

9:56

is a connected flow of different objects in a data set.

10:00

So I've got all of these transaction data

10:03

from different sources.

10:04

I have done a lot of cleaning that is common.

10:07

I've always objects in a single recipe

10:10

and then split into its respective destinations.

10:14

And these are the standard objects, like orders, assets,

10:17

services, service contracts, warranties, which primarily

10:20

deal with your IB use cases.

10:23

Now that this data would have been clean and enriched,

10:27

we also have a de-duplication service

10:30

where we can de-duplicate certain those locations

10:35

by whatever definition.

10:37

So you may say a combination of customer names,

10:39

the exact combination of location unique,

10:40

or just a combination of customer name

10:42

makes my accounts unique.

10:44

So as you can see here, this connects communication,

10:47

it is present across different systems.

10:49

And then we have brought all of them

10:51

as a part of the single cluster.

10:53

So this is how you de-duplicate your purchasing entities

10:58

or locations which help you unify your data

11:02

in a much better fashion.

11:05

Now that this cleaning and unification

11:08

will be done, we feed it to our analytics pipeline.

11:11

So we have a lot of services which work on this clean and unify

11:16

data and for better readability.

11:19

So I'll just show the configuration screen

11:21

where we have services both at a macro and a micro level.

11:26

At a macro level, we can generate what

11:28

is the propensity or probability that a location or transit

11:31

either part or an equipment or a service from you

11:35

in the next and number of days.

11:36

So once you train a model, you can use it for next and number

11:40

of days or you can train a new model based on data systems.

11:42

If based on the transaction history that you have got,

11:49

you can rank contacts by assigning a page

11:51

to their occurrences into different sources of the data.

11:55

And you can rank contact this, it typically

11:57

solves your whom to call problem.

11:59

Once you have opportunities created on the IV data.

12:03

We also have predictive and prescriptive opportunities

12:06

on the transaction history.

12:08

So you can generate opportunities at a micro level.

12:14

We would say that location X would transact item Y

12:18

in the next 90 days and this is the quantity and this is the

12:20

probability.

12:21

So this is and we call it as a purchase rate service.

12:25

At a micro level, we can segment your customers by usage

12:29

and the silver tellumer of parts and total number of

12:32

revenue that they would have generated.

12:34

We can also calculate the frequency, consistency and

12:37

recency of every purchasing entity or location.

12:40

What is the frequency between which they are buying?

12:41

What is the consistency?

12:43

And based on these metrics, we can also calculate

12:46

are your customers drifting away from you?

12:48

While a customer that was consistently buying from you has

12:52

that customer drifted away from you recently.

12:54

So these are the kind of information analytics that we

12:57

can generate at a macro and a micro level on that clean and

13:03

unified data.

13:04

So this is the USP of entire digital basically the studio

13:07

where we do all of this heavy lifting.

13:10

All of them under a single roof as you can see in this slide.

13:14

So you get data from different sources.

13:17

You perform, you do all the data stitching cleaning

13:22

unification.

13:23

We perform different purpose with analytics like calculating

13:27

a wallet share, a trend, propensity, and the predictive

13:32

and prescription opportunities that I spoke about a while ago.

13:35

And all of this can be viewed into a flagship product

13:40

which is the entire inside which gives you a 360 degree

13:42

visibility on your installments data where you can do

13:46

search or filtering or prioritize your hunting list.

13:50

You can also push this data directly into your CRM or into

13:54

data lakes.

13:54

We have customers who have given us access to their CRM

13:59

systems where we directly push it to their sales force or any

14:03

other system that would have configured.

14:07

We also have a lot of open APIs wherein our customers access

14:11

this clean and unified data via APIs.

14:15

And gain the value or basically derive maximum value on the

14:19

skin and unified data.

14:22

And one such example is how effortlessly we can integrate

14:26

this data into a sales force CRM.

14:29

So what you see, what you heard from me in the previous slides

14:33

before the past few minutes is all your major IB objects,

14:39

like equipments, parts, services, service contacts.

14:42

Once you have clean, enriched and unified that into the

14:45

entire install based intelligence platform, all of them can

14:48

be pulled seamlessly into your sales force account.

14:53

Thereby giving you a 360 degree view under a single roof

14:57

and giving you more than any opportunities and you can do

15:01

and there are endless possibilities to do things around

15:04

your install based data.

15:07

So this is what I had.

15:09

But today in the next webinar, we would be talking about

15:13

integration with sales force and also how

15:16

entitled analytics help our customers generate more revenue

15:21

by means of more predictive and prescriptive opportunities.

15:26

So with this, I would like to leave it to the audience for

15:30

any questions.

15:31

Yeah, we had a couple of questions come in.

15:37

So I'm going to ask you a question.

15:39

So I'm going to ask you a question.

15:41

So I'm going to ask you a question.

15:43

So I'm going to ask you a question.

15:45

So I'm going to ask you a question.

15:47

So I'm going to ask you a question.

15:49

So I'm going to ask you a question.

15:51

So I'm going to ask you a question.

15:53

So I'm going to ask you a question.

15:55

So I'm going to ask you a question.

15:57

So I'm going to ask you a question.

15:59

So I'm going to ask you a question.

16:01

So I'm going to ask you a question.

16:03

So I'm going to ask you a question.

16:05

So I'm going to ask you a question.

16:07

So I'm going to ask you a question.

16:09

So I'm going to ask you a question.

16:11

So I'm going to ask you a question.

16:13

So I'm going to ask you a question.

16:15

So I'm going to ask you a question.

16:17

So I'm going to ask you a question.

16:19

So I'm going to ask you a question.

16:21

So I'm going to ask you a question.

16:23

So I'm going to ask you a question.

16:25

So I'm going to ask you a question.

16:27

So I'm going to ask you a question.

16:29

So I'm going to ask you a question.

16:31

So I'm going to ask you a question.

16:33

And then we have another question here.

16:35

How easy is it to integrate and title with sales force?

16:39

And what does the add value it can give?

16:43

Yeah, so.

16:47

So it's a again a very good question.

16:49

And that's as you can see on my slide.

16:51

This is what you see once you have clean and identify data into your sales for

16:56

the account.

16:57

Where under that.

16:58

So under this I be intelligent staff just created by entitled.

17:01

You would see a 360 degree view of all your IB objects under a single tap.

17:09

So it's once the data is cleaned and unified.

17:13

The next step is pretty easy.

17:17

And we are basically we are very easy for our customers to have all of the data

17:23

under a single.

17:25

Right, they're keeping up with their current work flows that they have or the

17:28

current text set that they use.

17:29

But have the capability of expedited account research done all in front of them

17:37

Okay, that's all the questions that we had to come through today.

17:43

If anybody has any sort of follow up questions, please feel free to reach out

17:47

to us.

17:49

And we can get you connected to the right party here at entitled.

17:56

Right, with that being said, thanks everybody.

17:59

We look forward to seeing you in the next event.

18:03

Thank you.

Email

Become an Aftermarket Champion

Email

First Name

Last Name

Company Name

Job Title

Country

Search for

Is your Installed Base data a Mess?

0:00 - Let me go ahead and introduce our speaker of the day. ::: 0:04 - We have Shri Moondata, who has worked with in titles ::: 0:07 - for the past eight years. ::: 0:10 - He takes care of the entire data and DevOps infrastructure ::: 0:13 - for in title. ::: 0:14 - He has been instrumental in building ::: 0:16 - an in-salt-based data studio focused on industrial data ::: 0:20 - workflows, which he's going to go ahead and jump into ::: 0:22 - with that being said, Shri, all. ::: 0:24 - But you take it away. ::: 0:28 - Thanks a lot for the introduction, Colin. ::: 0:30 - Hello, everyone. ::: 0:31 - And thank you for joining our webinar today. ::: 0:33 - I'm excited to talk to you about a common challenge ::: 0:36 - based by industrial OEMs, which is managing the install ::: 0:40 - based data effectively. ::: 0:43 - Most of you would agree to this that this is a comprehensive ::: 0:47 - process. ::: 0:48 - And with the next few minutes, I'd like to shed light on, ::: 0:51 - how do we do it differently and repeatedly, and at a larger ::: 0:54 - scale at the end of the title? ::: 0:56 - So let's start with the scenario, which many of you ::: 1:00 - might be familiar with. ::: 1:01 - Your install based data, as you see in this slide, ::: 1:04 - would be scattered across various functional systems, ::: 1:06 - like CRM systems, ERP, FSM, different spreadsheets, ::: 1:11 - or e-commerce tools, legacy systems, and so on. ::: 1:14 - And each of the systems may hold valuable information, ::: 1:17 - but accessing and unifying this data can be a daunting task. ::: 1:21 - So it's like having all the pieces of the puzzle, ::: 1:24 - but not being able to see the complete picture. ::: 1:26 - And this is what we see across every single prospect ::: 1:30 - or customer that we talk to. ::: 1:32 - On top of that, the data here would be often messy, ::: 1:35 - inconsistent formats, duplicate entries, incomplete records. ::: 1:39 - It really makes it difficult to gain accurate insights ::: 1:42 - on to the data. ::: 1:43 - It becomes a big hindrance and leads to missed revenue ::: 1:47 - opportunities. ::: 1:49 - And this problem gets further compounded by the data silos. ::: 1:52 - And it's not that companies do not ::: 1:55 - make investments in this area, but thing ::: 1:57 - is the lack of a comprehensive process ::: 2:01 - around this data-fitting cleaning notification ::: 2:05 - leads to eventually get another silo. ::: 2:09 - So what's the solution? ::: 2:11 - And where does the entire comment to picture? ::: 2:13 - So what the entire list has done is ::: 2:15 - we have created a clean and unified process ::: 2:19 - that does the data cleaning enrichment analysis ::: 2:24 - on your IB data, which keeps your IB objects at the center. ::: 2:30 - So if we look at this data journey, ::: 2:32 - so here what we are striving is to transform your raw data ::: 2:37 - into actionable insights through the entire installation ::: 2:40 - platform. ::: 2:41 - So we begin by gathering the relevant data ::: 2:43 - from different systems. ::: 2:45 - Then we move to data exploration, where ::: 2:47 - we do a lot of everything on the data quality ::: 2:50 - and the data cleaning part of it, before feeding it ::: 2:53 - to analytics pipeline, where we have built certain custom ::: 2:56 - purpose-built models centered around the IB data. ::: 3:01 - And only when we have validated those results, ::: 3:06 - practice, set them, we push it to the final destination, ::: 3:11 - which are basically actionable intelligence, which ::: 3:15 - are accessed by our customers leading ::: 3:18 - into more new opportunities for them. ::: 3:21 - Having said that, the most crucial aspect in this journey ::: 3:24 - is the data quality, as it lays the foundation ::: 3:29 - for accurate analysis and generate ::: 3:32 - reliable insights in your IB data journey. ::: 3:35 - So we'll just deep dive into the data quality piece ::: 3:39 - because it has to be really comprehensive. ::: 3:43 - So if you take a step back and understand ::: 3:45 - what are the primary objects around the IB data? ::: 3:48 - So they could be transactions, equipments, ::: 3:52 - item master, bill of materials, service data, service ::: 3:56 - contact data, warrant these location masters, ::: 3:58 - and all of these data in real life ::: 4:00 - is scattered across different systems. ::: 4:02 - So the first thing is it should be cleaned and unified ::: 4:05 - and also enriched further so that you can ::: 4:09 - trick this into a high quality install base. ::: 4:12 - And during this process, it's also ::: 4:14 - important to have proper data governance and security ::: 4:16 - practices because it's important to ensure ::: 4:19 - integrity and protection of data. ::: 4:22 - But having said that, it's a very recent and done, ::: 4:25 - basically. ::: 4:26 - As you can see in this slide, cleaning and stitching ::: 4:29 - this install base data is a comprehensive process, ::: 4:32 - but it requires a lot of investment, ::: 4:34 - diverse skillsets, multiple tools, which ::: 4:37 - is really a time consuming and expensive thing to do. ::: 4:40 - So at the entitled, we have built something called ::: 4:43 - as a part of the installation platform. ::: 4:48 - We have built something called as the entire install base ::: 4:50 - data studio, which unifies all the data from all of your ::: 4:54 - different systems into a single cohesive system. ::: 4:58 - So this ensures that we achieve high quality data, ::: 5:03 - focused around your IB use cases, and on that high quality ::: 5:08 - data, we generate C60 degree analysis ::: 5:13 - like the parts of your training, equipment ::: 5:15 - training services, revenue training, identify the health ::: 5:17 - of your customers, both at a macro and micro level, ::: 5:20 - and make specific predictions and prescriptions ::: 5:24 - around equipments, opportunities, parts, opportunities, ::: 5:28 - and so on. ::: 5:29 - So at a high level, this is what our approach is. ::: 5:36 - What I do is I directly jump into our product demo ::: 5:39 - because the proof of the pudding is in the eating, ::: 5:42 - where I would actually show, what is it that entire install ::: 5:45 - base data studio has to offer and how do we do it? ::: 5:47 - As you can see here, into the IB data studio, ::: 5:54 - we have different workspaces for different personnel. ::: 5:56 - One is data prep workspace, where we do all the data ::: 6:00 - profiling, stitching, and cleaning, and stuff. ::: 6:03 - There is the analytic and the setup, basically, ::: 6:06 - the meta data management. ::: 6:08 - In the analytics, we have descriptive, predictive, ::: 6:10 - and predictive opportunities on the clean and unified IB data ::: 6:14 - that would have done into the data prep workspace. ::: 6:16 - Once we jump into the data prep workspace, ::: 6:18 - you would see a lot of services. ::: 6:20 - All of them are like self explanatory. ::: 6:21 - So data prep is where you prep all the data, ::: 6:24 - data loader, and data load is where we ingest this data ::: 6:28 - into our target systems. ::: 6:30 - And deduplication is where we deduplicate locations, ::: 6:34 - which is a common identifier across all different systems ::: 6:38 - that we have spoken about earlier. ::: 6:41 - So on the data acquisition side, you can upload file ::: 6:45 - from your local machine, or you can import directly ::: 6:47 - from your databases, import directly from snowflake. ::: 6:50 - And once you have imported data, we run several jobs ::: 6:54 - to profile that data. ::: 6:56 - So if I jump into one of the jobs, what you can see here ::: 6:59 - is a data distribution, which helps in identifying outliers, ::: 7:04 - missing values, the patterns in your data. ::: 7:07 - Or example, if I look at the report of this particular data ::: 7:10 - center that I have, it has roughly 150,000 records. ::: 7:14 - And 30% of the data is missing. ::: 7:18 - Now, if you look at this, you have different attributes, ::: 7:21 - cardinality, or different columns, which denotes ::: 7:24 - what are the, what is the, what how many number of records ::: 7:28 - in your data are distinct? ::: 7:29 - It will buy the book, why was it your book, ::: 7:32 - so you would identify any outliers in your data. ::: 7:35 - So doing this in the initial phase helps you really identify, ::: 7:39 - helps you identify how does my data quality look like? ::: 7:42 - Is this because if take a classic case where your data ::: 7:48 - may be lying into two to three different systems, ::: 7:49 - we could unify that and bring all of that data together. ::: 7:52 - And this gives you a unified picture of your data ::: 7:55 - distribution. ::: 7:55 - And then you can take a call on how do you improve the quality ::: 7:58 - of this data? ::: 7:59 - And if it is good, you move ahead, or if not, ::: 8:04 - you can perform several elementary and complex data ::: 8:08 - operations. ::: 8:09 - Some of them are merging a column, ::: 8:12 - was splitting a column, deleting it, renaming it ::: 8:14 - for better readability. ::: 8:16 - There are no code-local operations like find and replace, ::: 8:19 - find and replace by regular expressions. ::: 8:21 - You can just find by certain pattern and then replace it ::: 8:24 - by a specific value. ::: 8:27 - There are SQL type joins, where you can do left, right, ::: 8:31 - inner join on your data. ::: 8:34 - Then so I can choose a data set and do a left, right, inner join ::: 8:39 - also out a join with any other data set. ::: 8:41 - There are no code operations like create new column of type ::: 8:44 - string number, date, Boolean. ::: 8:46 - And you can perform various operations. ::: 8:48 - So if column A is empty and column B is not empty. ::: 8:51 - So different kind of no code things. ::: 8:54 - You can define a uniqueness criteria on your data. ::: 8:58 - You can say that a combination of n number of columns defines ::: 9:02 - my record as unique. ::: 9:04 - And what it is, it would drop duplicates. ::: 9:07 - That's how you keep unique records. ::: 9:10 - Then there are other operations like SQL type group ::: 9:13 - by or SQL type ranking functions, where you can group ::: 9:15 - by certain things and then you can use certain functions. ::: 9:19 - One of the use cases is you would have ::: 9:22 - caught some initial set of data from your system. ::: 9:24 - Now you want to apply an additional data to this. ::: 9:26 - So you can union it pattern matching ::: 9:30 - barricular expressions. ::: 9:31 - So you can count and extract matches ::: 9:33 - by certain regular expressions. ::: 9:35 - And the best part is whatever you do, ::: 9:37 - you can put this as a part of the recipe so that the next time ::: 9:42 - when you get similar data, you can rerun the same recipe step ::: 9:47 - that you had written earlier. ::: 9:50 - And what you are seeing here is something ::: 9:53 - called a ribic continuum, basically, which ::: 9:56 - is a connected flow of different objects in a data set. ::: 10:00 - So I've got all of these transaction data ::: 10:03 - from different sources. ::: 10:04 - I have done a lot of cleaning that is common. ::: 10:07 - I've always objects in a single recipe ::: 10:10 - and then split into its respective destinations. ::: 10:14 - And these are the standard objects, like orders, assets, ::: 10:17 - services, service contracts, warranties, which primarily ::: 10:20 - deal with your IB use cases. ::: 10:23 - Now that this data would have been clean and enriched, ::: 10:27 - we also have a de-duplication service ::: 10:30 - where we can de-duplicate certain those locations ::: 10:35 - by whatever definition. ::: 10:37 - So you may say a combination of customer names, ::: 10:39 - the exact combination of location unique, ::: 10:40 - or just a combination of customer name ::: 10:42 - makes my accounts unique. ::: 10:44 - So as you can see here, this connects communication, ::: 10:47 - it is present across different systems. ::: 10:49 - And then we have brought all of them ::: 10:51 - as a part of the single cluster. ::: 10:53 - So this is how you de-duplicate your purchasing entities ::: 10:58 - or locations which help you unify your data ::: 11:02 - in a much better fashion. ::: 11:05 - Now that this cleaning and unification ::: 11:08 - will be done, we feed it to our analytics pipeline. ::: 11:11 - So we have a lot of services which work on this clean and unify ::: 11:16 - data and for better readability. ::: 11:19 - So I'll just show the configuration screen ::: 11:21 - where we have services both at a macro and a micro level. ::: 11:26 - At a macro level, we can generate what ::: 11:28 - is the propensity or probability that a location or transit ::: 11:31 - either part or an equipment or a service from you ::: 11:35 - in the next and number of days. ::: 11:36 - So once you train a model, you can use it for next and number ::: 11:40 - of days or you can train a new model based on data systems. ::: 11:42 - If based on the transaction history that you have got, ::: 11:49 - you can rank contacts by assigning a page ::: 11:51 - to their occurrences into different sources of the data. ::: 11:55 - And you can rank contact this, it typically ::: 11:57 - solves your whom to call problem. ::: 11:59 - Once you have opportunities created on the IV data. ::: 12:03 - We also have predictive and prescriptive opportunities ::: 12:06 - on the transaction history. ::: 12:08 - So you can generate opportunities at a micro level. ::: 12:14 - We would say that location X would transact item Y ::: 12:18 - in the next 90 days and this is the quantity and this is the ::: 12:20 - probability. ::: 12:21 - So this is and we call it as a purchase rate service. ::: 12:25 - At a micro level, we can segment your customers by usage ::: 12:29 - and the silver tellumer of parts and total number of ::: 12:32 - revenue that they would have generated. ::: 12:34 - We can also calculate the frequency, consistency and ::: 12:37 - recency of every purchasing entity or location. ::: 12:40 - What is the frequency between which they are buying? ::: 12:41 - What is the consistency? ::: 12:43 - And based on these metrics, we can also calculate ::: 12:46 - are your customers drifting away from you? ::: 12:48 - While a customer that was consistently buying from you has ::: 12:52 - that customer drifted away from you recently. ::: 12:54 - So these are the kind of information analytics that we ::: 12:57 - can generate at a macro and a micro level on that clean and ::: 13:03 - unified data. ::: 13:04 - So this is the USP of entire digital basically the studio ::: 13:07 - where we do all of this heavy lifting. ::: 13:10 - All of them under a single roof as you can see in this slide. ::: 13:14 - So you get data from different sources. ::: 13:17 - You perform, you do all the data stitching cleaning ::: 13:22 - unification. ::: 13:23 - We perform different purpose with analytics like calculating ::: 13:27 - a wallet share, a trend, propensity, and the predictive ::: 13:32 - and prescription opportunities that I spoke about a while ago. ::: 13:35 - And all of this can be viewed into a flagship product ::: 13:40 - which is the entire inside which gives you a 360 degree ::: 13:42 - visibility on your installments data where you can do ::: 13:46 - search or filtering or prioritize your hunting list. ::: 13:50 - You can also push this data directly into your CRM or into ::: 13:54 - data lakes. ::: 13:54 - We have customers who have given us access to their CRM ::: 13:59 - systems where we directly push it to their sales force or any ::: 14:03 - other system that would have configured. ::: 14:07 - We also have a lot of open APIs wherein our customers access ::: 14:11 - this clean and unified data via APIs. ::: 14:15 - And gain the value or basically derive maximum value on the ::: 14:19 - skin and unified data. ::: 14:22 - And one such example is how effortlessly we can integrate ::: 14:26 - this data into a sales force CRM. ::: 14:29 - So what you see, what you heard from me in the previous slides ::: 14:33 - before the past few minutes is all your major IB objects, ::: 14:39 - like equipments, parts, services, service contacts. ::: 14:42 - Once you have clean, enriched and unified that into the ::: 14:45 - entire install based intelligence platform, all of them can ::: 14:48 - be pulled seamlessly into your sales force account. ::: 14:53 - Thereby giving you a 360 degree view under a single roof ::: 14:57 - and giving you more than any opportunities and you can do ::: 15:01 - and there are endless possibilities to do things around ::: 15:04 - your install based data. ::: 15:07 - So this is what I had. ::: 15:09 - But today in the next webinar, we would be talking about ::: 15:13 - integration with sales force and also how ::: 15:16 - entitled analytics help our customers generate more revenue ::: 15:21 - by means of more predictive and prescriptive opportunities. ::: 15:26 - So with this, I would like to leave it to the audience for ::: 15:30 - any questions. ::: 15:31 - Yeah, we had a couple of questions come in. ::: 15:37 - So I'm going to ask you a question. ::: 15:39 - So I'm going to ask you a question. ::: 15:41 - So I'm going to ask you a question. ::: 15:43 - So I'm going to ask you a question. ::: 15:45 - So I'm going to ask you a question. ::: 15:47 - So I'm going to ask you a question. ::: 15:49 - So I'm going to ask you a question. ::: 15:51 - So I'm going to ask you a question. ::: 15:53 - So I'm going to ask you a question. ::: 15:55 - So I'm going to ask you a question. ::: 15:57 - So I'm going to ask you a question. ::: 15:59 - So I'm going to ask you a question. ::: 16:01 - So I'm going to ask you a question. ::: 16:03 - So I'm going to ask you a question. ::: 16:05 - So I'm going to ask you a question. ::: 16:07 - So I'm going to ask you a question. ::: 16:09 - So I'm going to ask you a question. ::: 16:11 - So I'm going to ask you a question. ::: 16:13 - So I'm going to ask you a question. ::: 16:15 - So I'm going to ask you a question. ::: 16:17 - So I'm going to ask you a question. ::: 16:19 - So I'm going to ask you a question. ::: 16:21 - So I'm going to ask you a question. ::: 16:23 - So I'm going to ask you a question. ::: 16:25 - So I'm going to ask you a question. ::: 16:27 - So I'm going to ask you a question. ::: 16:29 - So I'm going to ask you a question. ::: 16:31 - So I'm going to ask you a question. ::: 16:33 - And then we have another question here. ::: 16:35 - How easy is it to integrate and title with sales force? ::: 16:39 - And what does the add value it can give? ::: 16:43 - Yeah, so. ::: 16:47 - So it's a again a very good question. ::: 16:49 - And that's as you can see on my slide. ::: 16:51 - This is what you see once you have clean and identify data into your sales for ::: 16:56 - the account. ::: 16:57 - Where under that. ::: 16:58 - So under this I be intelligent staff just created by entitled. ::: 17:01 - You would see a 360 degree view of all your IB objects under a single tap. ::: 17:09 - So it's once the data is cleaned and unified. ::: 17:13 - The next step is pretty easy. ::: 17:17 - And we are basically we are very easy for our customers to have all of the data ::: 17:23 - under a single. ::: 17:25 - Right, they're keeping up with their current work flows that they have or the ::: 17:28 - current text set that they use. ::: 17:29 - But have the capability of expedited account research done all in front of them ::: 17:37 - Okay, that's all the questions that we had to come through today. ::: 17:43 - If anybody has any sort of follow up questions, please feel free to reach out ::: 17:47 - to us. ::: 17:49 - And we can get you connected to the right party here at entitled. ::: 17:56 - Right, with that being said, thanks everybody. ::: 17:59 - We look forward to seeing you in the next event. ::: 18:03 - Thank you.