Slide 1

Slide 1 text

Sciencing Data Acquisition, Distillation & Consumption

Slide 2

Slide 2 text

Philip Tellis Principal RUM Distiller @ Akamai Author of the OpenSource boomerang RUM library twitter:@bluesmoon * github:@bluesmoon

Slide 3

Slide 3 text

What is Data Science?

Slide 4

Slide 4 text

A fancy term for Statistics?

Slide 5

Slide 5 text

A synonym for Computer Science?

Slide 6

Slide 6 text

A multi-disciplinary Art-Form... combining aspects of Statistics, Computing, Visual Storytelling, Domain Expertise, Typography, ,

Slide 7

Slide 7 text

At Akamai we primarily care about Internet Performance and Security

Slide 8

Slide 8 text

My team’s speciality is RUM

Slide 9

Slide 9 text

Search for patterns in data

Slide 10

Slide 10 text

Find abnormalities by determining what’s normal

Slide 11

Slide 11 text

Identify the parts of your site most important to your users

Slide 12

Slide 12 text

How does the performance of a website affect user behaviour?

Slide 13

Slide 13 text

OR ?

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

No content

Slide 16

Slide 16 text

Does emotional state affect our perception of latency?

Slide 17

Slide 17 text

Real Data ● ● ● ● Sports fans can get quite emotional!

Slide 18

Slide 18 text

The US was close to a win but Canada got a last minute leg in

Slide 19

Slide 19 text

But the web audience appeared to be prescient

Slide 20

Slide 20 text

● ● ● ●

Slide 21

Slide 21 text

● ● ●

Slide 22

Slide 22 text

● ● →

Slide 23

Slide 23 text

But what about Patience?

Slide 24

Slide 24 text

Definitions Load Time Error Tolerance LD 50 LD 25

Slide 25

Slide 25 text

Bounce Rate v/s Page Load Time for the entire game

Slide 26

Slide 26 text

1st & 2nd Period, Score: 0 - 0

Slide 27

Slide 27 text

3rd Period, US Leads 2 - 0

Slide 28

Slide 28 text

End of 3rd, Canada comes back 2 - 2

Slide 29

Slide 29 text

Canada wins 3 - 2

Slide 30

Slide 30 text

patience cultural significance Correlation?

Slide 31

Slide 31 text

LD 50 values for different countries DE ?? US 5.5s UK 11.5s AU ?? CA 13.5s 2.5

Slide 32

Slide 32 text

The importance of Domain Expertise ● structure of a hockey game ● understanding web performance ● biological sciences

Slide 33

Slide 33 text

Across domains, the Statistics used are often the same

Slide 34

Slide 34 text

We borrow from Economics The Product Space

Slide 35

Slide 35 text

...and Linguistic Anthropology

Slide 36

Slide 36 text

Navigating the Pacific ocean wind birds cloud star songs stories visualizations

Slide 37

Slide 37 text

Now to the boring stuff...

Slide 38

Slide 38 text

cleaned ● ● malicious ● anomalous Before we can analyze... normalized ● population ● time-zone ● currency

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

Interesting People Data

Slide 41

Slide 41 text

★ Understand ★ Borrow ★ ★ ★ story In Conclusion

Slide 42

Slide 42 text

Philip Tellis Principal RUM Distiller @ Akamai Author of the OpenSource boomerang RUM library twitter:@bluesmoon * github:@bluesmoon