So in this video, I want to talk about how with the
power of the customer data engine. Bloomreach is able to input any data point from any
of your data sources into its advanced machine
learning algorithms to accurately predict your customer's
actions.
And the best part is that these predictions will continue
to learn and update in real time.
As more data enters the platform,
Bloom reach offers a handful of out of the box
prediction templates such as purchase
likelihood optimal send time prediction
and even a custom prediction template that can
be used for creating a prediction specifically
tailored to your company's needs.
An example of this would be the best channel
prediction
which is able to identify the channel
which has the highest probability of leading to
the desired result. This could be clicks,
conversions, subscriptions
or any other custom metric. Here
we just have it set as purchase.
This will allow you to choose the right channel for each customer
maximizing the effectiveness of your campaigns.
It's also good to note that because these predictions
live on the customer profile level, they can
be used across the tool in segmentation
reporting recommendations.
Um and more. So let's see what these predictions
look like in action.
So we're looking here at our scenario builder,
uh just the typical abandoned browse
flow. So you can see it's triggered on when
somebody ends their session, it waits
a few hours, make sure that the customer
has not purchased recently, but
they have viewed items in the last 24
hours.
They will not send this campaign in the last week,
but here is where the predictions come
into play.
So I can drag and drop condition modules
wherever I need them
in the scenario, as you can see here.
And when you open up the condition modules,
they can be based on a customer attribute
as well as a customer action. In this
case, we'll do attribute
when I click this drop down, it shows
me everything from the customer profile, including
those predictions. So I'll pull in best
channel and set this one to S MS.
So they'll go down the yes branch
here. We'll make sure that they have given
consent for S MS and then we'll send them an S MS
message.
If that's not the river channel, we'll continue down
the no branch and we'll send them
email if that is their preferred channel
and they've consented.
And then last case scenario,
if they are not preferring email or
S MS, we'll send them to an ad audience for
rearing. Now, once that's all set, we
can go into the content itself and see how it's personalized
with the product data. So the Mackie
graphic T shirt,
if we head into the email, it'll be similar,
go ahead and go to the preview
and we can see here all of those products
uh and the product information like price and title
that the person was previously viewing.
So taking all of this into consideration within
a single flow, each recipient will be sent
messaging the way that is most preferable
to them based on this prediction.
And from a decision making standpoint, there's less
guessing and users are optimizing
their marketing spend.

In this video, I'll be walking through how you can use Bloomreach to process custom segments in real time
to power your personalized and up to date marketing
efforts.
Data and Bloomreach engagement is stored in
a no sequel schema list database structure.
So it's not a relational database. And
that means that all data that's ingested into
the platform from all of these different data sources
is accessible in real real time.
The platform is designed with the goal of speed
of access and use in mind along with
the end user experience as a priority.
So let's dive into the segment builder here
and see what this looks like. Now, I want
to build a segment of customers based on
customer lifetime value and purchase
recency. Let's start with customers
with high lifetime value and recent
purchases.
So I'll start by pulling in lifetime
value. I'll
set this to greater than
100.
I'll add one more filter condition here based
on purchase
and I want this to be from the last
six months.
And you can see I have that and logic here.
Now I can simply clone this
to build out the medium and the low categories.
But I'm just gonna go ahead and skip that for
now for the sake of time. And you can see
I already have been built out here. So I have
medium customer lifetime value is anything
greater than 50 and they've purchased
in the last year, but not the last six months.
Similarly, similarly, here
with low is anything,
you know, above one lower than 50
and then they purchased in the last two years, but
not the last 12 months.
You'll notice when I hit preview,
it populates instantly with no rendering time
right down here and our segmentation
update in real time as customers meet
or no longer meet the criteria. And this is
crucial especially during peak periods like
Black Friday, when we want to communicate with
our customers in a timely manner with the most up to
date information.
Let's say I want to send some of these customers to Facebook
for retargeting. I can simply click
into the chart
and click send campaign and
it will open up our scenario builder here.
Now I'll go ahead and drag in the
add audience module.
Now, I wanna send the customers with low lifetime
value and no recent purchases to Facebook
to try and reengage them from that channel.
So I'll just go ahead and link this here.
You can see the condition module is already set
up with that criteria.
So I'll say low
and no recent purchase.
On the other hand, I want to suppress my highly engaged
customers from all ad audiences since
they'll require, you know, less engaging.
And this is how that would look.
So I'll go ahead and clone this.
I'll change this from low,
too high.
You can do this down the no branch
and I'll go ahead and clone this here.
Now, within the modules themselves
here, I'll just come in click Facebook add integration,
have them added to an audience.
I'll just say value based customer
lifetime value audience and I'll base
this off of lifetime value.
And then for this one, I want to remove them from all audiences.
So again, I'll connect this integration here,
but I'm just gonna say remove from all
audiences.
So this automation
of audience cleansing will optimize
my marketing team's ad spend overall and then just
give the customers a more tailored experience.

A common goal for marketers is to automate the customer
journey while also keeping it hyper personalized
for each individual. So in this video, we'll
be walking through how to make sure each individual
customer receives your email campaign at
a time that they're most likely to click or open it
and they're shown product recommendations that
are likely to suit their needs. So if you
want to make sure that your subscribers receive emails at appropriate
times, bloom Rich Engagement offers an out
of the box
uh prediction template to calculate that optimal
send time
based on your customers past behavior. This feature
will predict the right hour for receiving an
email campaign for each of your subscribers
individually. And this can be optimized
based on either open or click, right? So
let's dive into what this looks like here.
I'll click into that template. It's gonna ask a
few quick questions.
So number one, how much data? So how far
back do we wanna look for email engagement?
I always like to go with three months since it's
fairly recent and up to date.
So number two, select the default if there's
not enough data to determine an optimal
sun time prediction. We will go with this default
value.
And then number three is just a quick
mapping question. So I'll say this
is gonna map to our campaign event
where the status
equals
clicked and
open.
All right. Now, once that is all set, I'll go
ahead and build out the recommendation
that we'll use in the email.
You'll also notice we have a set of recommendation
templates as well out of the box to give you a jumping
off point, I'm going to use
this one for customers who bought this
item also bought.
Now, this is gonna take a look at the entire
database of customers to figure out
what are common products that are purchased
amongst common sub segments of customers.
So I'll first select the product catalog here.
Number two. Again, it's just gonna be a quick mapping
question. So I'm gonna map that to purchase
item for specific product I DS
just defining what a purchase event is for
number three, the learning window.
Um I'm just gonna go back in all time for right
now for the blacklist option
here. This is saying I
don't wanna show products to a customer
if they've already purchased it or if they've already viewed
it or some other engagement criteria.
So for example, I would say purchase
item
product ready
in the last all time if the product
has a shelf life and it needs to be replaced
after a certain amount of time then I can set this
to be a relative time frame of, let's
say six
months. So once that six months is
up, the product will be reintroduced into
the recommendation algorithm.
Now, this last step here for customer preferences,
this is gonna take the power of the customer
data platform and the insights pulled from
the raw customer data and it's gonna
pair it with the product catalog data. So
when I enable this, I can say I
want a catalog
attribute here. So we'll say category level
three,
the category of the product must equal
the customer's category preference.
Right now, once I have all of this set up, I have the optimal
sun time prediction
configured as well as these recommendations.
The last step is to plug it into our scenario
or customer journey.
So I'll start this out here.
I'm gonna have this set up on a repeating cadence
here. I'll set it up to be
weekly on Mondays
that's good to go. And then I can
pull in the condition node here to
build out the audience from here.
I can actually set up my audience based
on customer actions or customer attributes.
This does include that prediction. So I
could pull that in here.
Or once I define the audience,
I can drag in this weight
module from down here
and open this up to say I want this to be based
on optimal send time prediction, whether
that's optimized for click the rate or open
rate. All right. And the
last step here is to pull in that email
and personalize it.
So I'm just gonna pick a template to
go off of.
I'll drag in dynamic content
configure this block to be
dark recommendations.
Select my recommendation model.
The one I just built out,
apply that
and head over to the test
preview to get a feel for
how this is gonna render differently for each
recipient.
All right. So by giving the customers
this hyper personalized experience, not only
does it decrease the amount of work and manual template
creation, the marketing team has to do, but
it will also increase the email engagement as
well as that customer lifetime value.

Hello. In this video, I'm going to
show a campaign that you can run in
Bloom reach engagement to boost repeat
repurchase rates with a frequency
based replenishment campaign.
This is gonna be a really valuable use case
to encourage your customers to repurchase
products that they've previously bought
and are likely to run out of soon
and or repurchase product services that
they are likely to buy again based
on frequency of purchase data.
This is gonna allow you to increase your customer
retention as well as increasing your
customer's lifetime value. So
in our example here, I'm in a Pacific pets
demo environment where we are going to run
a frequency based repurchase
campaign.
And while this does look scary, the complex,
the logic here is not all that
complex and this is a template or
plug and play use case. So every day
this campaign runs and it basically
looks for the varying cadence
that someone's purchases based on their past
behavior. We we we
have purchased information for each
of your customers, the dates that they
have purchased in the past. And we
basically create an average number of
days between their purchases, each
customer individually and when that
time is about to elapse, we
start to send them uh communications.
So if someone is purchasing only
every 30 or 60 days, they
only receive an email on day, 28
or day 58. And if someone's very
infrequently purchasing, based on their past behavior
every uh six months or every year
only, we would only start to send them
communications uh when it starts
to be around that time. So
uh the email itself, in this example
that they are going to receive is going to be
highly personalized as well. Where
in our frequency based repurchase
email, we want this to be as dynamic
as possible. So what we're going to do
using some of the templating language in bloom
reach engagement in our email here is
actually uh we're going to,
if I pull up an example customer Jenny,
we're going to calculate and display the number of
days since we've seen uh their, their
last purchase events. This Edith
here is actually the pet name. This is a pet
uh demo environment. So Edith has a dog
named or sorry, Jenny has a
dog named Edith and
uh she has previously purchased this product
for that dog. So that's the product here.
And so we're prompting this person to replenish
that purchase, maybe they're running low and we're also
displaying other product
recommendations.
So this is gonna be a really useful campaign.
You would set something like this up one
time and it would just rerun every
day. It would also readjust the cadence
based on uh the updating
uh purchase behavior of each of your customers.
And then it would start to send them this remo find
your email around that time.
So, uh these really help to improve
customer engagement, customer retention, loyalty
to your brands uh and can even help
you to reduce churn by giving
your customers the reminder they might need to
repurchase from you and not someone else.

Hello. In this short video, I'm going to talk about
how you can use Bloomreach engagement
to identify and segment
audiences that are serial
returners.
One of the great things about Bloomer engagement
is our flexibility. Just
like we would typically store
purchase related information, we
can also store and commonly do
store return information as
well. So every customer might
make purchases, they might also
make returns and all of that is stored
associated to each customer record
in the form of events. And what we
can do with events is calculate values.
In this case, I've created a couple aggregates
for each customer that is going
to count the number of items that they purchased
as well as the items that they
have returned. So while
Daisy has purchased a lot of products,
five of them, in fact, she's returned
most of those products four out of
the five. So one of the things we've
done here is we've created a segmentation
to put people into a return rate band.
And in this case, she's in the high
band which is greater than 60%.
So my return rate segmentation
which is here has high mid low
and never returners. So my customers
are going to fall into one of these bands
depending on the number of items that they have
returned after purchasing. So
I have a lot of high returners in this example.
Well, what do I want to do with those high
returners? One kind of low
hanging fruit would be maybe we just want
to target them very frequently on
the website with information
about our size guides or things
like that. So we can create
a campaign called a web layer
which would overlay or sit on
top of our existing site as
a pop up or a banner. In
this case, I'm just calling this size guide.
And it's centered over the page where
uh we are saying hi friend need help with sizing.
And then this would hyperlink to
some size guide that you might have published.
And this uh the great thing about
web layers in bloom reach engagement is that
we can be very specific about our audience.
We don't want to serve this to the people that we've
identified as never returners
because they can size themselves just fine. We
can under settings specify
our audience here as only
customers that are in a particular return
rate segment. So I can say the return rate
segment which I've just selected
here from my saved segmentation
equals the high segment. So these
are my segments as previously shown,
which is now going to be 6500
matched customers. So only those people
that are the serial returners that have
the high return rate would be kind
of prompted with the return
uh with the size guide web layer
upon their sessions. So really low
hanging fruit here, very simple to set this up
and identify these customers. And this can
help drastically to reduce your business's
return rate, which is of course, a very
costly thing.