19
The Physics of Everyday Life Bayesian Neural Networks in Business Applications Big Data User Group July 2013 Meetup in Karlsruhe Dr. F. Wick, Blue Yonder GmbH & Co. KG [email protected]

The Physics of Everyday life

Embed Size (px)

DESCRIPTION

The combination of Bayesian statistics and neural networks has proven to excel in predictive analytics. Blue Yonders solution NeuroBayes was developed and applied first in the field of particle physics but it can be successfully applied to a broad range of everyday problems for example demand prediction in retail. In this talk we introduce the basic concepts and explain the structure, components, and operations that build up an application for prediction.

Citation preview

Page 1: The Physics of Everyday life

The Physics of Everyday Life Bayesian Neural Networks in Business Applications

Big Data User Group – July 2013 Meetup in Karlsruhe

Dr. F. Wick, Blue Yonder GmbH & Co. KG

[email protected]

Page 2: The Physics of Everyday life

Our Background: High Energy Physics Fundamental research at the forefront of science

A few key questions in High Energy Physics:

» Our current theoretical understanding is called the

“Standard Model”

» Extremely well tested, some of its aspects have the most

precise agreement between theoretical predictions and

experimental results across all sciences

» What happened at the beginning of the universe?

» Does our theory remain valid under such extreme conditions

or is it a “low energy approximation” of a more fundamental

theory?

» What is the origin of mass? A Higgs boson has been found

» Is it the Higgs boson?

» Why is there so much matter left in the universe?

» All matter should have annihilated with anti-matter,

where does this asymmetry come from?

Photo: CERN DI-2-8-91

The Physics of Everyday Life July 2013 2

Page 3: The Physics of Everyday life

The Large Hadron Collider at CERN Built to understand how exactly our universe works

Schreiben Sie hier Ihren Text

LHC: 27km circumference

Photo: CERN

The Physics of Everyday Life July 2013 3

Page 4: The Physics of Everyday life

Big Data in Particle Physics

At the LHC (CERN) - per experiment:

• 40 000 000 events per second

• up to 1 PetaByte per second raw data

• 1 PB of data get stored per year

searching for the needle in the hay stack…

Need to filter out the „interesting“

events in real-time

Photo: CERN

The Physics of Everyday Life July 2013 4

Page 5: The Physics of Everyday life

Artificial Neural Networks and NeuroBayes

The Physics of Everyday Life

► NeuroBayes classification core based on simple

feed forward neural network

► Information coded in connections between neurons

► Each neuron performs fuzzy decisions

► Neural networks learn from examples

► Human brain: about 1011 neurons

about 1014 connections

► NeuroBayes: 10 to few 100 neurons

July 2013 5

Page 6: The Physics of Everyday life

Bayes‘ Theorem and NeuroBayes

The Physics of Everyday Life

Posterior Evidence

Likelihood Prior

► NeuroBayes internally uses Bayesian arguments for regularisation

► NeuroBayes automatically makes Bayesian posterior statements

July 2013 6

Page 7: The Physics of Everyday life

A little more Detail

The Physics of Everyday Life July 2013 7

Page 8: The Physics of Everyday life

Mode I: Classification Issues

The Physics of Everyday Life

Classification:

Binary targets: Each single outcome will be “yes“ or “no“

NeuroBayes output is the Bayesian posterior probability that answer is “yes“

(given that inclusive rates are the same in training and test sample, otherwise simple

transformation necessary).

Examples:

► This elementary particle is a muon.

► Customer Meier will cancel his contract next year.

July 2013 8

Page 9: The Physics of Everyday life

Probability density for real valued

targets:

For each possible (real) value a

probability (density) is given. From

that all statistical quantities like mean

value, median, mode, standard

deviation, etc. can be deduced.

Mode II: Regression Issues

The Physics of Everyday Life

Examples:

► Energy of an elementary particle

► Turnaround of an article next year

July 2013 9

Page 10: The Physics of Everyday life

Historic or simulated

data

Data set a = ... b = ... c = ... .... t = …!

NeuroBayes® Teacher

NeuroBayes® Expert

New or real data

Data set a = ... b = ... c = ... .... t = ?

Expertise

Expert system

f t

Probability that hypothesis

is correct (classification)

or probability density

for variable t

t

How it works: Training and Prediction

The Physics of Everyday Life July 2013 10

Page 11: The Physics of Everyday life

What does the future hold?

What would

happen if...

... a large supermarket chain knew precisely how much fresh fruit it will sell?

The Physics of Everyday Life July 2013 11

Page 12: The Physics of Everyday life

Blue Yonder – forward looking, forward thinking

Now about 100 employees of which

most are post-docs, mainly from HEP.

Doubling our numbers in 2012, 2013 is

looking good…

3 Offices:

Karlsruhe, Hamburg (Germany)

London (UK)

Started as a spin-off from the

University of Karlsruhe, Germany

supported by the Federal Ministry

for Education and Research.

The Physics of Everyday Life July 2013 12

Page 13: The Physics of Everyday life

Use all available and relevant

information as input, e.g.

measurements from the various

sub-detectors, …

NeuroBayes will extract statistically

significant patterns in the data to derive

the prediction.

Prediction will return the best

estimator for a measurement

including a statistically sound

estimation of the expected

spread.

100 Energy

Momentum

Direction

Type

50

90

Sub-Detector

Distance 200

Calo

Kaon

...

pro

pability

P

Particle Property

E(X)

NeuroBayes from Science to Industry Predictive Analytics in High Energy Physics

The Physics of Everyday Life July 2013 13

Page 14: The Physics of Everyday life

Use all available and relevant

information as input, e.g. article

properties, previous sales, etc

NeuroBayes will extract statistically

significant patterns in the data to derive

the prediction.

Prediction will return e.g. the most

probable sales rate including a

statistically sound estimation of

the expected spread.

Article size

Picture size

colour

Previous sales

M

21%

red

brand

price 19,9

171

24

...

pro

pability

P

Prediction sales

E(X)

NeuroBayes from Science to Industry Predictive Analytics in industry

E.g. Retail

NeuroBayes allows data-driven analysis and forecasts – both in science and industry

The Physics of Everyday Life July 2013 14

Page 15: The Physics of Everyday life

Automated replenishment

in supermarkets

Fondsmanagement

Insurance:

Risk prediction

Fashion:

Sales prediction

Media

Churn Management

Artikelabsatz P

E(X)=413

Stock Exchange

Order Placement System

SAP

NeuroBayes®

NeuroBayes from Science to Industry Predictive Analytics is the key to many industries

The Physics of Everyday Life July 2013 15

Page 16: The Physics of Everyday life

» Most conventional methods: Forecast is a single number

» No estimate how precise this number is

» Does not allow to handle asymmetric distribution of probabilities

» NeuroBayes: Prediction of a full probability density distribution

Asymmetric

probability density

distribution

X1: most probable value

(n.b. all other values may still occur)

P (x)

quantity(x)

x1

Optimal estimate for

your use-case

X2: Median: 50% of all values are smaller, 50% larger than this x2

Get more from the Forecasts

The Physics of Everyday Life July 2013 16

Page 17: The Physics of Everyday life

Conclusion

» Exploiting “Big data” is the next “big” challenge to advance industry

» “In this war for customers, the ammunition is data — and lots of it […]” (G. Hawkings, Harvard Business Review, Sep. 2012)

» This is the day and age of Predictive Analytics

» Data-driven business instead of models and assumptions

» Peta-bytes of data and machine learning techniques allow statistically sound analyses

» Blue Yonder: From “Big Science” to “Big Business”

» Background in High Energy Physics: Crossing the bridge from understanding the

behaviour of the fundamental particles at the origin of the universe to the “Big Bang” in

sales forecast, risk analysis, churn management, etc.

» Versatile NeuroBayes machine learning solution allows to optimise a wide range of

business cases

The Physics of Everyday Life July 2013 17

Page 18: The Physics of Everyday life

Thank you very much For your attention!

Page 19: The Physics of Everyday life

Disclaimer

This Presentation (the Presentation) has been prepared by Blue Yonder GmbH & Co KG (collectively, with any officer, director, employee, advisor or agent of any of them,

the Preparers) for the purpose of setting out certain confidential information in respect of Blue Yonder’s business activities and strategy. References to the “Presentation”

includes any information which has been or may be supplied in writing or orally in connection with the Presentation or in connection with any further inquiries in respect

of the Presentation. This Presentation is for the exclusive use of the recipients to whom it is addressed.

This Presentation and the information contained herein is confidential. In addition to the terms of any confidentiality undertaking that a recipient may have entered into

with Blue Yonder, by its acceptance of the Presentation, each recipient agrees that it will not, and it will procure that each of its agents, representatives, advisors, directors

or employees (collectively, Representatives), will not, and will not permit any third party to, copy, reproduce or distribute to others this Presentation, in whole or in part, at

any time without the prior written consent of Blue Yonder, and that it will keep confidential all information contained herein not already in the public domain and will use

this Presentation for the sole purpose of setting out [familiarizing itself with] certain limited background information concerning Blue Yonder and its business strategy and

activities. The foregoing confidentiality obligation shall be legally binding for the recipient infinitely. This Presentation is not intended to serve as basis for any investment

decision. If a recipient has signed a confidentiality undertaking with Blue Yonder, this Presentation also constitutes Confidential Information for the purposes of such

undertaking.

While the information contained in this Presentation is believed to be accurate, the Preparers have not conducted any investigation with respect to such information. The

Preparers expressly disclaim any and all liability for representations or warranties, expressed or implied, contained in, or for omissions from, this Presentation or any

other written or oral communication transmitted to any interested party in connection with this Presentation so far as is permitted by law. In particular, but without

limitation, no representation or warranty is given as to the achievement or reasonableness of, and no reliance should be placed on, any projections, estimates, forecasts,

analyses or forward looking statements contained in this Presentation which involve by their nature a number of risks, uncertainties or assumptions that could cause

actual results or events to differ materially from those expressed or implied in this Presentation. Only those particular representations and warranties which may be made

in a definitive written agreement, when and if one is executed, and subject to such limitations and restrictions as may be specified in such agreement, shall have any legal

effect. By its acceptance hereof, each recipient agrees that none of the Preparers nor any of their respective Representatives shall be liable for any direct, indirect or

consequential loss or damages suffered by any person as a result of relying on any statement in or omission from this Presentation, along with other information

furnished in connection therewith, and any such liability is expressly disclaimed.

Except to the extent otherwise indicated, this Presentation presents information as of the date hereof. The delivery of this Presentation shall not, under any circumstances,

create any implication that there will be no change in the affairs of Blue Yonder after the date hereof. In furnishing this Presentation, the Preparers reserve the right to

amend or replace this Presentation at any time and undertake no obligation to update any of the information contained in the Presentation or to correct any inaccuracies

that may become apparent.

This Presentation shall remain the property of Blue Yonder. Blue Yonder may, at any time, request any recipient, or its Representatives, shall promptly deliver to Blue

Yonder or, if directed in writing by Blue Yonder, destroy all confidential information relating to this Presentation received in written, electronic or other tangible form

whatsoever, including without limitation all copies, reproductions, computer diskettes or written materials which contain such confidential information. At such time, all

other notes, analyses or compilations constituting or containing confidential information in the recipient’s, or their Representatives’, possession shall be destroyed. Such

destruction shall be certified to Blue Yonder by the recipient in writing. Neither the dissemination of this Presentation nor any part of its contents is to be taken as any form

of commitment on the part of the Preparers or any of their respective affiliates to enter any contract or otherwise create any legally binding obligation or commitment. The

Preparers expressly reserve the right, in their absolute discretion, without prior notice and without any liability to any recipient to terminate discussions with any recipient

or any other parties.

The distribution of this Presentation in certain jurisdictions may be restricted by law and, accordingly, recipients of this Presentation represent that they are able to receive

this Presentation without contravention of any unfulfilled registration requirements or other legal restrictions in the jurisdiction in which they reside or conduct business.

July 2013 The Physics of Everyday Life 19