馃攳
Data Science in 8 Minutes | Data Science for Beginners | What is Data Science? | Edureka - YouTube
Channel: edureka!
[10]
We hear a lot about
how artificial intelligence
[13]
and machine learning
are going to change the world
[16]
and how the internet
[17]
of things will make
everyone's life easier.
[19]
But what's the one thing
[21]
that underpins all of these
revolutionary Technologies?
[24]
The answer is data.
[25]
From social media to
the iot devices for generating.
[29]
Bill amount of data consider
the cab service provider Uber.
[33]
I'm sure all of you
have used Uber.
[35]
What are you think makes
[37]
Uber a multi-billion
dollar worth company.
[40]
Is it that availability
of cabs or is it their service?
[43]
Well, the answer is
data data makes them very rich,
[47]
but wait, is there enough
to grow a business?
[51]
Of course, it
isn't you must know
[53]
how to use the data
to draw useful insights
[55]
and solve problems.
[57]
This is where data
science comes in in.
[59]
Words data science is
the process of using
[62]
data to find Solutions
[63]
or to predict outcomes
[65]
for a problem statement to
better understand data science.
[68]
Let's see how it affects
our day-to-day activities.
[71]
It's a Monday morning
and I have to get to office
[74]
before my meeting starts.
[75]
So I quickly open up Uber
and look for cabs,
[78]
but there's something
unusual the gab reads
[81]
A comparatively higher
at this hour of the day.
[84]
Why does this happen?
[85]
Well, obviously because
Monday mornings are
[87]
P cars and everyone
is rushing off to work.
[90]
Work the high demand
for cams leads to increase
[93]
in the cab fares.
[94]
We all know this
[95]
but how is all of
this implemented data science is
[98]
at the heart of Ubers pricing
algorithm The Surge pricing
[101]
algorithm ensures
[102]
that their passengers
always get a ride
[105]
when they need one.
[106]
Even if it comes at the cost
of inflated prices
[109]
Uber implements data science
to find out which neighborhoods
[112]
will be the busiest
[114]
so that it can activate
search pricing to get
[116]
more drivers on the road
in this manner over maximized.
[120]
The number of rides it
can provide and hence benefit
[123]
from this Uber surge pricing
algorithm uses data science.
[126]
Let's see how a data science
process always begins
[130]
with understanding the business
requirement or the problem.
[133]
You're trying to
solve in this case.
[135]
The business requirement is
to build a dynamic pricing model
[138]
that takes effect.
[140]
When a lot of people
[141]
in the same area are requesting
rides at the same time.
[144]
This is followed by
[146]
data collection Uber collects
data such as the weather.
[149]
Oracle data holidays time
traffic pick up
[153]
and drop location
[154]
and it keeps a track
of all of this.
[156]
The next stage is data cleaning
[158]
while sometimes unnecessary data
[160]
is collected such data only
increases the complexity
[164]
of the problem an example is
boober might collect information
[168]
like the location of restaurants
[170]
and cafes nearby now such data
[171]
is not needed to analyze
Uber surge pricing there
[175]
for such data has to be removed
[177]
at this step data planning
is followed by date.
[180]
Exploration and Analysis.
[181]
The data exploration stage is
[183]
like the brainstorming
of data analysis.
[186]
This is where you understand
the patterns in your data.
[189]
This is followed by data
modeling the data modeling stage
[193]
basically includes building
a machine learning model
[196]
that predicts the Uber surge
at a given time and location.
[199]
This model is built
by using all the insights
[202]
and Trends collected
in the exploration stage.
[205]
The model is trained
by feeding at thousands
[207]
of customer records,
[209]
so that it can Learn to predict
the outcome more precisely.
[212]
Next is the data
validation stage now
[215]
here the model is tested
[216]
when a new customer books
arrive the data
[219]
of the new booking is compared
[220]
with the historic data
in order to check
[223]
if there are any anomalies
in the search prices
[225]
or any false predictions,
[227]
if any such anomalies
are detected a notification
[230]
is immediately sent to
the data scientists at Uber
[233]
who fix the issue.
[234]
This is how Uber
predicts a surge price
[237]
for a given location
[238]
and time the final stage
of The science is deployment
[241]
and optimization.
[242]
So after testing the model
and improving its efficiency,
[245]
it is deployed on all the users
at this stage customer feedback
[249]
is received and
if there are any issues,
[252]
they are fixed here.
[253]
So that was the entire
data science process.
[256]
Now, let's look
at a few other applications
[258]
of data science data
science is implemented
[261]
in e-commerce platforms,
[263]
like Amazon and Flipkart.
[264]
It is also
[265]
the logic behind Netflix's
recommendation system now
[268]
in all actuality Qu
ality data science
[271]
has made remarkable changes
in today's market.
[274]
It's applications range
from credit card fraud detection
[277]
to self-driving cars
[279]
and virtual assistant
such as City and Alexa.
[282]
Let's consider an example
suppose you look
[285]
for shoes on Amazon,
[286]
but you do not buy
it then in there.
[288]
Now the next day you're watching
videos on YouTube
[291]
and suddenly you see an ad
for the same item you switch
[294]
to Facebook there.
[295]
Also, you see the same ad
so how does this happen?
[299]
Well this Happens
[300]
because Google Tracks
your search history
[302]
and recommends ads based
on your search history.
[305]
This is one of the coolest
applications of data science.
[308]
In fact 35% of Amazon's
revenue is generated
[312]
by product recommendation.
[314]
And the logic behind product
recommendation is data science.
[318]
Let me tell you another sad
story Scott killed in
[321]
never imagined his Apple watch
might save his life,
[324]
but that's exactly
what happened a few months ago
[327]
when he had a heart attack
in the middle of the night.
[330]
But how could a watch detect
a heart attack any guesses?
[333]
Well, it's data science again.
[335]
Apple used data science
to build a watch
[338]
that monitors
[338]
and individuals Health
this watch collects data
[342]
such as the person's
[343]
heart rate sleep cycle
breathing rate activity
[346]
level blood pressure Etc
and keeps a record
[349]
of these measures 24 bars seven.
[352]
This collected data
is then processed
[354]
and analyzed to build a model
[356]
that predicts the risk
of a heart attack.
[358]
So these were a few
hours Locations now
[361]
the question is how
[362]
and why you should become
a data scientist
[365]
according to linkedin's
March 2019 survey
[368]
a data scientist is the most
promising job role in the US
[372]
and it stands at number one on
glass doors best jobs of 2019.
[377]
Here are a couple of job trends
[379]
that are collected
from LinkedIn top companies
[382]
like Microsoft IBM Facebook
[384]
and Google have
over thousand job vacancies,
[387]
and this number
is only going to grow.
[389]
Hurley these job Trends
show the vacancy of jobs
[392]
with respect to jog defame
coming to the salary
[395]
of a data scientist
the average salary ranges
[398]
between a hundred thousand
dollars two hundred
[400]
and eighty two thousand dollars.
[402]
Now remember that
your salary varies
[405]
on your skills your level
of experience your geography
[408]
and the company you're working
for here are the skills
[411]
that are needed to become
a data scientist.
[413]
You must be skilled
[414]
in statistics expertise in
programming languages like our
[418]
and python is a Just
[420]
you're required to have a good
understanding of processes,
[423]
like data extraction processing
wrangling and exploration.
[427]
You must also be well-versed
with the different types
[429]
of machine learning algorithms
[431]
and how they work Advanced
machine learning Concepts
[434]
like deep learning is also
needed you must also possess
[437]
a good understanding
[438]
of the different big
data processing Frameworks,
[441]
like Hadoop and
Spark and finally,
[443]
you must know how to visualize
the data by using tools
[446]
like Tableau and power bi now
[448]
that you know what it takes
to become a data scientist.
[451]
It's time to buckle up
[453]
and kick start your career
as a data scientist.
[456]
That's all from my side guys.
[457]
If you wish to learn more about
such trending Technologies,
[461]
make sure you subscribe
to our Channel
[463]
until next time happy learning.
[465]
I hope you have enjoyed
listening to this video.
[468]
Please be kind enough to like it
[470]
and you can comment any
of your doubts and queries
[473]
and we will reply them
[475]
at the earliest do look out
for more videos in our playlist
[479]
and To Edureka channel
to learn more.
[482]
Happy learning
Most Recent Videos:
You can go back to the homepage right here: Homepage