Select Page

Datasciencing Customer Demographics with Power BI

by | Dec 15, 2022 | Uncategorized | 0 comments

Join our founder, Peter Koebel, as he walks through datasciencing customer demographics with Power BI.

Datasciencing can be tough, but does it have to be? Check out this demonstration on Datasciencing Customer Demographics with Power BI.

Read the video transcription below:

hi I’m Peter Keobel from Datasciencing Consultants,

making another video


past I’ve made a lot of videos showing

off dashboards in a microsoft excel and

tableau but some people have asked me

about treating dashboards in power bi so

in this video here I will be showing off

a power bi dashboard alright so if you

ready let’s have some data fun

so this dashboard you can see here we

have map of Canada this is where the

showing the gross sales and the count of

the number of customers in each of these

provinces and over here we had so here

Anto was the largest so that’s where the

most sales are that’s where the company

is headed this is just a sample dataset

this isn’t a real data but it looks like

it’s based in Manitoba

and over here is total sales forces for

all our customers just a thousand

customers in this dataset and the

average sale is $16 seven used two cents

so what we can do here in power bi is

use some dynamic filters do some basic

data mining to check out what’s going on

with our customers so for example here

these are categories handmade vintage

antique furniture miscellaneous and here

is another chart their agent gender

split up male female and here are age

groups down the side here so if we

wanted we could check out just all

information about our handmade or

handmade products so there’s 756

customers bought our handmade products

the average sale is a bit less than the

average self all our products so though

this is the highest total sales the

average sale is a bit less and the

demographics here did not change too

much from our

overall demographics one thing we can do

is notice that most of our customers

here are females in these three age

groups so we can highlight these 18 25

26 to 35 and 36 to 45 and we can see

here represents almost half our

customers 46% however the average sale

is far less than the average sale of our

regular or the overall customer data set

and the sales are a lot less so we have

more customers in this group but not as

much sales so not buying as much so we

can focus on either focus on possibly

seen if we can even increase the price

of those products or for looking market

more volume if these are going to be

lower profit margin items that they are

buying to try to increase try to to take

advantage of the high number of

customers in that area that demographic

you can also see here how many customers

in each province all of these 400 ice

460 sorry hundred ninety three of them

are in Manitoba so we could focus on a

campaign man Toba and spread it out or

Saskatchewan here is more central

through prayer promises in their 70s so

that might also be feasible instead of

trying to do a nationwide campaign focus

on a smaller group for a store over here

there is you see there’s only 48 so that

might not be as useful as sketch one


so I’ll deselect these to go back to our

base sets this is for all our

information so we can also click on that

say one what’s going on just in

Saskatchewan can see over all our 150

customers and ten thousand South

thousands dollars with the sales there’s

not much going on there the high profit

margin items so we can explore and see

what other provinces might be somewhere

to focus on if we’re looking for the

higher-end items we see it there all

look the same so there isn’t anyone

other than men tobe here’s a bit higher

but there isn’t any promises they’re

showing like average of twenty dollars a

sales so that can kind of also confirm

that D average sells fairly consistent

terms of promises that’s not necessarily

a huge huge or big splash information

but it’s also good to know when you’re

making decisions you won’t be confident

what you’re making decisions based on if

that’s what you suspect or you suspect

almost your customers are Manitoba this

will confirm that so

even when your data money does have to

be totally relative like totally new

information unit know about just also

help just confirm what your suspected

already from your experience working in

with all your customers over the years

so we can also go different and check

out the lowest number here of customers

or the smallest number of different

customers here are the 64 plus if you

one market that group you maybe expand

that and see what’s going on there so

you see we only have 45 customers but

the average sale is almost $23 which is

significantly higher than the average

sale of all our customers

so might be worth checking out

specifically what they’re all the

products they’re buying and focus on

marketing towards this age group as they

seem to be spending the most and most

likely have the higher profit margin

items that might be worth it in contrast

to the other each demographics trying to

sell a few more products but a higher

profit margin might in the end make more

profit than focusing on just quantity

here with this age group with the lower

average sales is probably lower profit

margin so that’s some basic data mining

we can do here in power bi we can also

check out say just by our categories

explore what’s going on their categories

so our vintage items average sale is

quite a bit lower than our yourself

overall customers and we almost have 500

customers in this group as well I didn’t

hear it because these are going to be

overlap so we have some customers that

are mind handing me to add vintage

that’s why these totals will add up to

more than a thousand if we just look at

handmade and vintage who can see here

handmade the average sales close to the

regular average sale so let’s see what

else is going on antiques is quite a bit

higher so maybe that’s also another

group category to focus on and we can

explore let’s see what else is okay it’s

a furniture average sales so furniture

is probably more expensive so we could

check the profit margin see if that’s

worth exploring more and where the most

customers are of course mantou that’s

where it’s based there’s still a fair

number in Saskatchewan Alberta here only

two and British Columbia so maybe with

shipping us

might you’re not worth it doesn’t look

there’s any Ontario there’s a few in

Quebec so if you want to focus on

furniture sales you have a new furniture

product because its sales quite high I

could probably ask start in Manitoba or

Saskatchewan and focus on that area and

capture some good revenue in them in

those areas in this for your furnish

kegger and here’s the miscellaneous that

significantly lower somebody not one

focus or focus on scene whatever you

need to improve or if it’s worth keeping

those miscellaneous items that you’re

selling so this is yeah just a basic

power bi dashboard doing a little bit of

data mining to see where I look for

marketing or type of items you want to

focus on interests in using dashboards

to improve your business making

decisions you can check up decide

CENTCOM or email me at Peter koe de L at

dais on Singh Kham thanks for watching

Likert Scales in Tableau

If you need help with your Python, machine learning, or Jupyter, I’m Peter Koebel the owner of Data Sciencing Consultants. You can reach me at 204-770-6437, or email me at, or fill out the form on our website  You can also check out our YouTube channel for more awesome Excel tips!

For more awesome python and machine learning tips, like this one about likert scales in Tableau, check out the Datasciencing Consultants blog.

Looking for more fun with data? You might enjoy some of our other posts!

US Population Density Map using Tableau Join our founder, Peter Koebel as he demonstrates a population density map using Tableau. You've probably seen population density visualizations everywhere, but how can you use them in your own...