SlideShare une entreprise Scribd logo
1  sur  27
Télécharger pour lire hors ligne
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Big Data
Modelos Predictivos
Retos y generación de nuevas soluciones
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
360 Customer
View
Connections
without boundaries
Incredible Speed
and Reliability
The promise…
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
3
Cambie sus creencias!
+ preguntas, + modelos,
+ Citizen Data Scientists
Menos Servidores,
Mas Distributed Poweful Laptops
- Hadoop, - Spark+,
- CODIGO!
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Part 1: Who are we?
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Dr. Ir. Frank Vanden Berghen
Phd. In Applied-Sciences with specialization in applied-
mathematics (mathematical optimization)
Building predictive models for more than 15 years, all around
the world.
Top winners at various world-level datamining competitions:
5
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
6
Automation
Moore’s Law
Lifeofa
Modelos Predictivos
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
7
Objectives & Motivations
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
8
At University
IRIDIA=Research in Artificial Intelligence
Neural Networks
One Tree
Forest of Trees
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
9
In consulting… Far from AI…
VS
Now: Manual & Archaic
(1 to 3 months to get 1 Model)
Self-Learning &
Auto-Adaptative
Artificial Intelligence
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
10
Market Reality: all is Scoring
Quien? Que?
X SELL
UP SELL
CHURN
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Typical difficulties:
• High Bayes-Error Levels
• Small Target Size (<1%)
• Scalability Issues
• Before all: TIME!
•AUTOMATED?
11
Churn, cross-sell, and up-sell models aren’t easy
TIME! THERE IS NO TIME!
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Inventsomething
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Usual time to create one model for a datamining competition: 1 to 3 months
13
Ultimate Accuracy & No Free Lunch
Competition Metric Winner
TIMi
(or similar
automated tool)
Difference
Heritage Health Price Some kind of R² 46.12% 46.24% 0.12%
AUSDM2009 (following Netflix) AUC 69.41% 69.24% 0.17%
Kaggle Axa Telematics 2015 AUC 96.35% 95.97% 0.38%
PAKDD2007 AUC 70.01% 69.28% 0.73%
PAKDD2010* AUC 64.10% 63.30% 0.80%
KDD2009-upselling AUC 90.92% 89.94% 0.98%
Datascience.net Axacross-selling2015 Lift at 10% 26.09% 24.74% 1.35%
KDD2009-churn AUC 76.51% 74.74% 1.77%
KDD2009-appetency AUC 88.19% 86.31% 1.88%
“No free lunch”: There will always exists a specific modeling algorithm
that surpasses a “generic, general-purpose & automated tool”
*: winning entry removed because it used additional external data and that’s cheating
Look here
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Sales
A typical time-line for a SAS,IBM,R project:
14
Back in 2010
A typical time-line for a TIMi project:
idea
Data Preparation Model
Total: 1 – 3 meses. Modelo: 2-6 weeks
Total: 2 – 6 WEEKS. Modelo: 1-5 DAYSidea
ETL
MODEL
CREATI
VITY
RUNTI
ME
Sales
ETL
MODEL
CREATI
VITY
RUNTI
ME
Sales
FUN
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Part 2:Moore’s Law…
…In real life
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Moore’s Law:
“The number of transistors that can
be fit on a computer chip will double
every two years, resulting in periodic
increases in computing power.”
16
I despise Moore’s law!
 FAST implementation, slow runtime
 No attention to code quality
 “Algorithmic complexity” ?
 Efficient code = LOSING TIME
Direct
consequence of
Moore’s Law:
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
17
An observation: Moore’s Law is (somewhat) “broken”
Source: “Computing Performance: Game Over or Next Level?” from
Samuel H. Fuller, Analog Devices Inc. and Lynette I. Millett, National
Research Council
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
18
Moore’s Law is broken: …and it’s terrible!
Exponential Growth
of Data Volumes
Technologies such as RFID and smartphones as well as the increasing use
of social media application are resulting in a rapid rise in data volumes
(Practically) No Growth
in CPU speed
Expectation Gap:
factor of 10
Expectation Gap:
factor of 1000
Expectation Gap:
factor of 100
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
19
Moore’s Law is broken: 2 Solutions
• Low-Level Assembler &
C code
• Mathematical “tricks”
• Algorithmic
It’s the “seventies solution”
• High-Level (i.e. slow) Language (i.e. Java & Spark)
• Computing farm
Supported by:
• “Legacy”
• Cloud services (Warning: Linear price-grid!)
• Consulting Companies
• Coders without any Assembler/C or algorithmic knowledge
This is a possible solution if your wallet can grow
exponentially with the size of your data. This will
ultimately lead to high cost linked to legacy software.
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
20
OPEN
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Infrastructure
Complexity
Implementation (Time)
Hadoop, Exadata and others cost hundreds of thousands of dollars
Data mining requires PhD’s with years of experience in the field
Implementing predictive models or complex KPI can take months or more to
be integrated in the business processes
Storage
Data can be stored in a highly compressed file format that allows to store (and process) all the
data from a 10 millions telecom for 3 years on one simple laptop
Barriers to entry for “Big Data”
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Complexity
Do you need Phd in stats to
answer analytical questions?
(See also the concept of “Citizen Developer here:
http://www.gartner.com/it-glossary/citizen-
developer/ )
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Complexity
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
Deal with Big Data
on a laptop: Live
demo!
24
Scale of Solution
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
On my laptop:
• Compute a aggregate on a table with 17 columns and 1.3 billion rows: 70 seconds
(finest granularity for 2 years of ticket data from a larger retailer with 1 million customer)
• Sort a (CDR) table with 8 columns and 1 billion rows: 120 seconds.
(finest granularity for 2 month of CDR data from a telecom with 5 millions subscribers)
• Create 3 KDD-Grade-Predictive models (for churn, cross-sell, up-sell) on a learning
dataset (from the KDD2009) with 50K rows and 15K columns (and than apply this
model on the same scoring dataset): 20 minutes (about 7 minutes per model)
The laptop has: Core i7 CPU at 2.4 GHz and a simple SSD drive.
25
Storage and computational Speed Live Demo!
Conclusion: A simple laptop is enough to store & process all your data,
whatever the size, the origin, the granularity, the type or the format of the data.
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
26
© 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions.
27
… to boldly go where no dataminer has bone before!

Contenu connexe

Tendances

TechConnectr's Big Data Connection. Digital Marketing KPIs, Targeting, Analy...
TechConnectr's Big Data Connection.  Digital Marketing KPIs, Targeting, Analy...TechConnectr's Big Data Connection.  Digital Marketing KPIs, Targeting, Analy...
TechConnectr's Big Data Connection. Digital Marketing KPIs, Targeting, Analy...Bob Samuels
 
The true meaning of data by Maciej Dabrowski
The true meaning of data by Maciej Dabrowski   The true meaning of data by Maciej Dabrowski
The true meaning of data by Maciej Dabrowski Altocloud
 
The true meaning of data
The true meaning of dataThe true meaning of data
The true meaning of datamdabrowski
 
Webinar: Building a Data-Driven, Customer Focused Business
Webinar: Building a Data-Driven, Customer Focused BusinessWebinar: Building a Data-Driven, Customer Focused Business
Webinar: Building a Data-Driven, Customer Focused BusinessLinkedIn
 
855 sponsor gazdak_using our laptop
855 sponsor gazdak_using our laptop855 sponsor gazdak_using our laptop
855 sponsor gazdak_using our laptopRising Media, Inc.
 
How artificial intelligence (AI) can help maximize customer intelligence ROI
How artificial intelligence (AI) can help maximize customer intelligence ROIHow artificial intelligence (AI) can help maximize customer intelligence ROI
How artificial intelligence (AI) can help maximize customer intelligence ROIVincent de Stoecklin
 
AI projects - Lifecyle & Best Practices
AI projects - Lifecyle & Best PracticesAI projects - Lifecyle & Best Practices
AI projects - Lifecyle & Best PracticesVincent de Stoecklin
 
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)Data Driven Innovation
 
Big Data for the Retail Business I Swan Insights I Solvay Business School
Big Data for the Retail Business I Swan Insights I Solvay Business SchoolBig Data for the Retail Business I Swan Insights I Solvay Business School
Big Data for the Retail Business I Swan Insights I Solvay Business SchoolLaurent Kinet
 
Marketing with Linked Data (MIT)
Marketing with Linked Data (MIT)Marketing with Linked Data (MIT)
Marketing with Linked Data (MIT)Scott Brinker
 
Scott Brinker - The State of Marketing Technology 2017/2018
Scott Brinker - The State of Marketing Technology 2017/2018Scott Brinker - The State of Marketing Technology 2017/2018
Scott Brinker - The State of Marketing Technology 2017/2018Martech Alliance
 
Big data’s Last Crusade
Big data’s Last CrusadeBig data’s Last Crusade
Big data’s Last CrusadeDipock Das
 
Building the Cognitive Era : Big Data Strategies
Building the Cognitive Era : Big Data StrategiesBuilding the Cognitive Era : Big Data Strategies
Building the Cognitive Era : Big Data StrategiesKevin Sigliano
 
A visual approach to fraud detection and investigation - Giuseppe Francavilla
A visual approach to fraud detection and investigation - Giuseppe FrancavillaA visual approach to fraud detection and investigation - Giuseppe Francavilla
A visual approach to fraud detection and investigation - Giuseppe FrancavillaData Driven Innovation
 
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...TigerGraph
 
Fraudulent credit card cash-out detection On Graphs
Fraudulent credit card cash-out detection On GraphsFraudulent credit card cash-out detection On Graphs
Fraudulent credit card cash-out detection On GraphsTigerGraph
 
The state of marketing measurement, attribution and data management
The state of marketing measurement, attribution and data managementThe state of marketing measurement, attribution and data management
The state of marketing measurement, attribution and data managementClark Boyd
 
Correspondent Banking Networks
Correspondent Banking NetworksCorrespondent Banking Networks
Correspondent Banking NetworksTigerGraph
 
Fix, don't stitch: be a steward of your marketing data
Fix, don't stitch: be a steward of your marketing dataFix, don't stitch: be a steward of your marketing data
Fix, don't stitch: be a steward of your marketing dataMAD//Fest London
 

Tendances (20)

TechConnectr's Big Data Connection. Digital Marketing KPIs, Targeting, Analy...
TechConnectr's Big Data Connection.  Digital Marketing KPIs, Targeting, Analy...TechConnectr's Big Data Connection.  Digital Marketing KPIs, Targeting, Analy...
TechConnectr's Big Data Connection. Digital Marketing KPIs, Targeting, Analy...
 
The true meaning of data by Maciej Dabrowski
The true meaning of data by Maciej Dabrowski   The true meaning of data by Maciej Dabrowski
The true meaning of data by Maciej Dabrowski
 
The true meaning of data
The true meaning of dataThe true meaning of data
The true meaning of data
 
Webinar: Building a Data-Driven, Customer Focused Business
Webinar: Building a Data-Driven, Customer Focused BusinessWebinar: Building a Data-Driven, Customer Focused Business
Webinar: Building a Data-Driven, Customer Focused Business
 
855 sponsor gazdak_using our laptop
855 sponsor gazdak_using our laptop855 sponsor gazdak_using our laptop
855 sponsor gazdak_using our laptop
 
How artificial intelligence (AI) can help maximize customer intelligence ROI
How artificial intelligence (AI) can help maximize customer intelligence ROIHow artificial intelligence (AI) can help maximize customer intelligence ROI
How artificial intelligence (AI) can help maximize customer intelligence ROI
 
AI projects - Lifecyle & Best Practices
AI projects - Lifecyle & Best PracticesAI projects - Lifecyle & Best Practices
AI projects - Lifecyle & Best Practices
 
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)
How AI will impact Web and Social Media Intelligence - Uljan Sharka (Crystal.io)
 
Big Data for the Retail Business I Swan Insights I Solvay Business School
Big Data for the Retail Business I Swan Insights I Solvay Business SchoolBig Data for the Retail Business I Swan Insights I Solvay Business School
Big Data for the Retail Business I Swan Insights I Solvay Business School
 
Marketing with Linked Data (MIT)
Marketing with Linked Data (MIT)Marketing with Linked Data (MIT)
Marketing with Linked Data (MIT)
 
Scott Brinker - The State of Marketing Technology 2017/2018
Scott Brinker - The State of Marketing Technology 2017/2018Scott Brinker - The State of Marketing Technology 2017/2018
Scott Brinker - The State of Marketing Technology 2017/2018
 
Big data’s Last Crusade
Big data’s Last CrusadeBig data’s Last Crusade
Big data’s Last Crusade
 
Building the Cognitive Era : Big Data Strategies
Building the Cognitive Era : Big Data StrategiesBuilding the Cognitive Era : Big Data Strategies
Building the Cognitive Era : Big Data Strategies
 
A visual approach to fraud detection and investigation - Giuseppe Francavilla
A visual approach to fraud detection and investigation - Giuseppe FrancavillaA visual approach to fraud detection and investigation - Giuseppe Francavilla
A visual approach to fraud detection and investigation - Giuseppe Francavilla
 
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...
Graph Gurus Episode 34: Graph Databases are Changing the Fraud Detection and ...
 
Ques data mining
Ques data miningQues data mining
Ques data mining
 
Fraudulent credit card cash-out detection On Graphs
Fraudulent credit card cash-out detection On GraphsFraudulent credit card cash-out detection On Graphs
Fraudulent credit card cash-out detection On Graphs
 
The state of marketing measurement, attribution and data management
The state of marketing measurement, attribution and data managementThe state of marketing measurement, attribution and data management
The state of marketing measurement, attribution and data management
 
Correspondent Banking Networks
Correspondent Banking NetworksCorrespondent Banking Networks
Correspondent Banking Networks
 
Fix, don't stitch: be a steward of your marketing data
Fix, don't stitch: be a steward of your marketing dataFix, don't stitch: be a steward of your marketing data
Fix, don't stitch: be a steward of your marketing data
 

En vedette

Big y Open Data para las Smart Cities
Big y Open Data para las Smart CitiesBig y Open Data para las Smart Cities
Big y Open Data para las Smart CitiesBig-Data-Summit
 
Estrategias omnicanal para la mejora de los procesos de comunicación y marke...
	Estrategias omnicanal para la mejora de los procesos de comunicación y marke...	Estrategias omnicanal para la mejora de los procesos de comunicación y marke...
Estrategias omnicanal para la mejora de los procesos de comunicación y marke...Big-Data-Summit
 
Lost in Translation: Connecting Data Insights with Marketing Execution
Lost in Translation: Connecting Data Insights with Marketing ExecutionLost in Translation: Connecting Data Insights with Marketing Execution
Lost in Translation: Connecting Data Insights with Marketing ExecutionBig-Data-Summit
 
Data Visualization & Data Storytelling
Data Visualization & Data StorytellingData Visualization & Data Storytelling
Data Visualization & Data StorytellingBig-Data-Summit
 
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo Cambiante
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo CambianteBig Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo Cambiante
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo CambianteBig-Data-Summit
 
Big Data en salud: Un mundo de posibilidades
Big Data en salud: Un mundo de posibilidadesBig Data en salud: Un mundo de posibilidades
Big Data en salud: Un mundo de posibilidadesBig-Data-Summit
 
Convergencia de Analítica con la Experiencia Digital
Convergencia de Analítica con la Experiencia DigitalConvergencia de Analítica con la Experiencia Digital
Convergencia de Analítica con la Experiencia DigitalBig-Data-Summit
 
Explorando los Límites de la Predicción
Explorando los Límites de la PredicciónExplorando los Límites de la Predicción
Explorando los Límites de la PredicciónBig-Data-Summit
 
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadas
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadasParadigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadas
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadasBig-Data-Summit
 
Data Science: De la Matemática a la Práctica
Data Science: De la Matemática a la PrácticaData Science: De la Matemática a la Práctica
Data Science: De la Matemática a la PrácticaBig-Data-Summit
 
Métodos predictivos y Descriptivos - MINERÍA DE DATOS
Métodos predictivos y Descriptivos - MINERÍA DE DATOSMétodos predictivos y Descriptivos - MINERÍA DE DATOS
Métodos predictivos y Descriptivos - MINERÍA DE DATOSlalopg
 
Internet de las cosas
Internet de las cosasInternet de las cosas
Internet de las cosasAnnie Higuera
 
Procesamiento de datos a gran escala con Apache Spark
Procesamiento de datos a gran escala con Apache SparkProcesamiento de datos a gran escala con Apache Spark
Procesamiento de datos a gran escala con Apache SparkSoftware Guru
 
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...INACAP
 
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...UNIVERSIDAD MAGISTER (Sitio Oficial)
 
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)pmluque
 
Big Data and Internet of Things: Creating Customer Value for the Internet of ...
Big Data and Internet of Things:Creating Customer Value for the Internet of ...Big Data and Internet of Things:Creating Customer Value for the Internet of ...
Big Data and Internet of Things: Creating Customer Value for the Internet of ...Red Bend Software
 
Big Data con Sql Server 2014 y la nube
Big Data con Sql Server 2014 y la nubeBig Data con Sql Server 2014 y la nube
Big Data con Sql Server 2014 y la nubeEduardo Castro
 
Modelos de propensión en la era del Big Data
Modelos de propensión en la era del Big DataModelos de propensión en la era del Big Data
Modelos de propensión en la era del Big DataAlex Rayón Jerez
 

En vedette (20)

Big y Open Data para las Smart Cities
Big y Open Data para las Smart CitiesBig y Open Data para las Smart Cities
Big y Open Data para las Smart Cities
 
Estrategias omnicanal para la mejora de los procesos de comunicación y marke...
	Estrategias omnicanal para la mejora de los procesos de comunicación y marke...	Estrategias omnicanal para la mejora de los procesos de comunicación y marke...
Estrategias omnicanal para la mejora de los procesos de comunicación y marke...
 
Lost in Translation: Connecting Data Insights with Marketing Execution
Lost in Translation: Connecting Data Insights with Marketing ExecutionLost in Translation: Connecting Data Insights with Marketing Execution
Lost in Translation: Connecting Data Insights with Marketing Execution
 
Data Visualization & Data Storytelling
Data Visualization & Data StorytellingData Visualization & Data Storytelling
Data Visualization & Data Storytelling
 
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo Cambiante
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo CambianteBig Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo Cambiante
Big Data e Internet de las Cosas: Nuevas Tecnologías para un Mundo Cambiante
 
Big Data en salud: Un mundo de posibilidades
Big Data en salud: Un mundo de posibilidadesBig Data en salud: Un mundo de posibilidades
Big Data en salud: Un mundo de posibilidades
 
Convergencia de Analítica con la Experiencia Digital
Convergencia de Analítica con la Experiencia DigitalConvergencia de Analítica con la Experiencia Digital
Convergencia de Analítica con la Experiencia Digital
 
Explorando los Límites de la Predicción
Explorando los Límites de la PredicciónExplorando los Límites de la Predicción
Explorando los Límites de la Predicción
 
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadas
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadasParadigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadas
Paradigmas de Procesamiento en Big Data: Arquitecturas y Tecnologías aplicadas
 
Data Science: De la Matemática a la Práctica
Data Science: De la Matemática a la PrácticaData Science: De la Matemática a la Práctica
Data Science: De la Matemática a la Práctica
 
Métodos predictivos y Descriptivos - MINERÍA DE DATOS
Métodos predictivos y Descriptivos - MINERÍA DE DATOSMétodos predictivos y Descriptivos - MINERÍA DE DATOS
Métodos predictivos y Descriptivos - MINERÍA DE DATOS
 
Internet de las cosas
Internet de las cosasInternet de las cosas
Internet de las cosas
 
Big data
Big dataBig data
Big data
 
Procesamiento de datos a gran escala con Apache Spark
Procesamiento de datos a gran escala con Apache SparkProcesamiento de datos a gran escala con Apache Spark
Procesamiento de datos a gran escala con Apache Spark
 
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...
Sra. Karin Quiroga, Internet de las Cosas y Big Data: ¿hacia dónde va la Indu...
 
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...
Evaluación del Sistema de Procesamiento de Grabdes Volúmenes de Datos Científ...
 
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)
BIG DATA en CLOUD PaaS para Internet de las Cosas (IoT)
 
Big Data and Internet of Things: Creating Customer Value for the Internet of ...
Big Data and Internet of Things:Creating Customer Value for the Internet of ...Big Data and Internet of Things:Creating Customer Value for the Internet of ...
Big Data and Internet of Things: Creating Customer Value for the Internet of ...
 
Big Data con Sql Server 2014 y la nube
Big Data con Sql Server 2014 y la nubeBig Data con Sql Server 2014 y la nube
Big Data con Sql Server 2014 y la nube
 
Modelos de propensión en la era del Big Data
Modelos de propensión en la era del Big DataModelos de propensión en la era del Big Data
Modelos de propensión en la era del Big Data
 

Similaire à TIMi: Faster predictions on big data with laptops

Jakarta presentation
Jakarta presentationJakarta presentation
Jakarta presentationGil Brown
 
3 Keys for Digital Transformation in Manufacturing
3 Keys for Digital Transformation in Manufacturing3 Keys for Digital Transformation in Manufacturing
3 Keys for Digital Transformation in ManufacturingPlex Systems
 
Data mining with big data implementation
Data mining with big data implementationData mining with big data implementation
Data mining with big data implementationSandip Tipayle Patil
 
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013Craig Rispin
 
Modernizing Architecture for a Complete Data Strategy
Modernizing Architecture for a Complete Data StrategyModernizing Architecture for a Complete Data Strategy
Modernizing Architecture for a Complete Data StrategyCloudera, Inc.
 
How to Wrangle Data for Machine Learning on AWS
 How to Wrangle Data for Machine Learning on AWS How to Wrangle Data for Machine Learning on AWS
How to Wrangle Data for Machine Learning on AWSAmazon Web Services
 
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...Eka Software Solutions
 
The Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninThe Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninInside Analysis
 
Saama-POI Summit Speaker Deck April 2016 Final
Saama-POI Summit Speaker Deck April 2016 FinalSaama-POI Summit Speaker Deck April 2016 Final
Saama-POI Summit Speaker Deck April 2016 FinalDan Maxwell
 
Research Presentation: How Numbers are Powering the Next Era of Marketing
Research Presentation: How Numbers are Powering the Next Era of MarketingResearch Presentation: How Numbers are Powering the Next Era of Marketing
Research Presentation: How Numbers are Powering the Next Era of MarketingMediaPost
 
Ntegra 20180523 v10 copy.pptx
Ntegra 20180523 v10 copy.pptxNtegra 20180523 v10 copy.pptx
Ntegra 20180523 v10 copy.pptxISSIP
 
The Journey to Big Data Analytics
The Journey to Big Data AnalyticsThe Journey to Big Data Analytics
The Journey to Big Data AnalyticsDr.Stefan Radtke
 
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...The Lima Consulting Group Digital Transformation Maturity Model Presented at ...
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...Lima Consulting Group
 
Bigdata Landscape and Competitive Intelligence
Bigdata Landscape and Competitive IntelligenceBigdata Landscape and Competitive Intelligence
Bigdata Landscape and Competitive IntelligenceJithin S L
 
Sweden future of ai 20180921 v7
Sweden future of ai 20180921 v7Sweden future of ai 20180921 v7
Sweden future of ai 20180921 v7ISSIP
 
Open power meetup at h2o 20180325 v3
Open power meetup at h2o 20180325 v3Open power meetup at h2o 20180325 v3
Open power meetup at h2o 20180325 v3ISSIP
 
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...InterCon
 
Impact of big data on analytics
Impact of big data on analyticsImpact of big data on analytics
Impact of big data on analyticsCapgemini
 

Similaire à TIMi: Faster predictions on big data with laptops (20)

Jakarta presentation
Jakarta presentationJakarta presentation
Jakarta presentation
 
3 Keys for Digital Transformation in Manufacturing
3 Keys for Digital Transformation in Manufacturing3 Keys for Digital Transformation in Manufacturing
3 Keys for Digital Transformation in Manufacturing
 
Data mining with big data implementation
Data mining with big data implementationData mining with big data implementation
Data mining with big data implementation
 
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013
ALPMA - Craig Rispin's Keynote & Workshop 18 Oct 2013
 
Modernizing Architecture for a Complete Data Strategy
Modernizing Architecture for a Complete Data StrategyModernizing Architecture for a Complete Data Strategy
Modernizing Architecture for a Complete Data Strategy
 
How to Wrangle Data for Machine Learning on AWS
 How to Wrangle Data for Machine Learning on AWS How to Wrangle Data for Machine Learning on AWS
How to Wrangle Data for Machine Learning on AWS
 
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...
Webinar: Why Commodity Analytics is the Next Big Thing for Trading, Risk, & S...
 
The Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine LearninThe Sky’s the Limit – The Rise of Machine Learnin
The Sky’s the Limit – The Rise of Machine Learnin
 
Saama-POI Summit Speaker Deck April 2016 Final
Saama-POI Summit Speaker Deck April 2016 FinalSaama-POI Summit Speaker Deck April 2016 Final
Saama-POI Summit Speaker Deck April 2016 Final
 
Research Presentation: How Numbers are Powering the Next Era of Marketing
Research Presentation: How Numbers are Powering the Next Era of MarketingResearch Presentation: How Numbers are Powering the Next Era of Marketing
Research Presentation: How Numbers are Powering the Next Era of Marketing
 
Ntegra 20180523 v10 copy.pptx
Ntegra 20180523 v10 copy.pptxNtegra 20180523 v10 copy.pptx
Ntegra 20180523 v10 copy.pptx
 
The Journey to Big Data Analytics
The Journey to Big Data AnalyticsThe Journey to Big Data Analytics
The Journey to Big Data Analytics
 
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...The Lima Consulting Group Digital Transformation Maturity Model Presented at ...
The Lima Consulting Group Digital Transformation Maturity Model Presented at ...
 
Bigdata Landscape and Competitive Intelligence
Bigdata Landscape and Competitive IntelligenceBigdata Landscape and Competitive Intelligence
Bigdata Landscape and Competitive Intelligence
 
Solving Big Data Industry Use Cases with AWS Cloud Computing
Solving Big Data Industry Use Cases with AWS Cloud ComputingSolving Big Data Industry Use Cases with AWS Cloud Computing
Solving Big Data Industry Use Cases with AWS Cloud Computing
 
Sweden future of ai 20180921 v7
Sweden future of ai 20180921 v7Sweden future of ai 20180921 v7
Sweden future of ai 20180921 v7
 
Open power meetup at h2o 20180325 v3
Open power meetup at h2o 20180325 v3Open power meetup at h2o 20180325 v3
Open power meetup at h2o 20180325 v3
 
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...
Data is the New Oil: Presented By Naveen Narayanan, Global Client Partner of ...
 
Data Mining With Big Data
Data Mining With Big DataData Mining With Big Data
Data Mining With Big Data
 
Impact of big data on analytics
Impact of big data on analyticsImpact of big data on analytics
Impact of big data on analytics
 

Plus de Big-Data-Summit

SafeHomeFace - Sistema de reconocimiento facial.
SafeHomeFace - Sistema de reconocimiento facial.SafeHomeFace - Sistema de reconocimiento facial.
SafeHomeFace - Sistema de reconocimiento facial.Big-Data-Summit
 
Las 10 tendencias principales de BI para el 2018 - Carloz Díaz
Las 10 tendencias principales de BI para el 2018 - Carloz DíazLas 10 tendencias principales de BI para el 2018 - Carloz Díaz
Las 10 tendencias principales de BI para el 2018 - Carloz DíazBig-Data-Summit
 
El big data analytics donde menos te lo esperas - Alex Rayón
El big data analytics donde menos te lo esperas - Alex RayónEl big data analytics donde menos te lo esperas - Alex Rayón
El big data analytics donde menos te lo esperas - Alex RayónBig-Data-Summit
 
Big Data en el sector inmobiliario - Gonzalo Martín
Big Data en el sector inmobiliario - Gonzalo MartínBig Data en el sector inmobiliario - Gonzalo Martín
Big Data en el sector inmobiliario - Gonzalo MartínBig-Data-Summit
 
Modelo Operativo para grandes proyectos de AI - Ignacio Marrero
Modelo Operativo para grandes proyectos de AI - Ignacio MarreroModelo Operativo para grandes proyectos de AI - Ignacio Marrero
Modelo Operativo para grandes proyectos de AI - Ignacio MarreroBig-Data-Summit
 
La evolución de la analítica descriptiva - Diego Aguirre
La evolución de la analítica descriptiva - Diego AguirreLa evolución de la analítica descriptiva - Diego Aguirre
La evolución de la analítica descriptiva - Diego AguirreBig-Data-Summit
 
El dato tiene forma y la forma significado - Josep Curto
El dato tiene forma y la forma significado - Josep CurtoEl dato tiene forma y la forma significado - Josep Curto
El dato tiene forma y la forma significado - Josep CurtoBig-Data-Summit
 
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentes
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentesBDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentes
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentesBig-Data-Summit
 
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos Digitales
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos DigitalesBDAS-2017 | Deep Learning para Extracción de Valor en Contenidos Digitales
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos DigitalesBig-Data-Summit
 
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...Big-Data-Summit
 
BDAS-2017 | sanselix jobranke_rpptx
BDAS-2017 | sanselix jobranke_rpptxBDAS-2017 | sanselix jobranke_rpptx
BDAS-2017 | sanselix jobranke_rpptxBig-Data-Summit
 
BDAS-2017 | Analitica visual presentación mlms2
BDAS-2017 | Analitica visual presentación mlms2BDAS-2017 | Analitica visual presentación mlms2
BDAS-2017 | Analitica visual presentación mlms2Big-Data-Summit
 
BDAS-2017 | Comunidad Data Science
BDAS-2017 | Comunidad Data ScienceBDAS-2017 | Comunidad Data Science
BDAS-2017 | Comunidad Data ScienceBig-Data-Summit
 
BDAS-2017 | DMC Challengue concurso satisfacción universidad
BDAS-2017 | DMC Challengue concurso satisfacción universidadBDAS-2017 | DMC Challengue concurso satisfacción universidad
BDAS-2017 | DMC Challengue concurso satisfacción universidadBig-Data-Summit
 
BDAS-2017 | Hanldling Target Bias in Predictive Modelling
BDAS-2017 | Hanldling Target Bias in Predictive ModellingBDAS-2017 | Hanldling Target Bias in Predictive Modelling
BDAS-2017 | Hanldling Target Bias in Predictive ModellingBig-Data-Summit
 
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendencias
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendenciasBDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendencias
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendenciasBig-Data-Summit
 
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...Big-Data-Summit
 
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big Data
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big DataBDAS-2017 | Comprendiendo nuestras motivaciones a través de Big Data
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big DataBig-Data-Summit
 
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...Big-Data-Summit
 
Building Innovative Data Products in a Banking Environment
Building Innovative Data Products in a Banking EnvironmentBuilding Innovative Data Products in a Banking Environment
Building Innovative Data Products in a Banking EnvironmentBig-Data-Summit
 

Plus de Big-Data-Summit (20)

SafeHomeFace - Sistema de reconocimiento facial.
SafeHomeFace - Sistema de reconocimiento facial.SafeHomeFace - Sistema de reconocimiento facial.
SafeHomeFace - Sistema de reconocimiento facial.
 
Las 10 tendencias principales de BI para el 2018 - Carloz Díaz
Las 10 tendencias principales de BI para el 2018 - Carloz DíazLas 10 tendencias principales de BI para el 2018 - Carloz Díaz
Las 10 tendencias principales de BI para el 2018 - Carloz Díaz
 
El big data analytics donde menos te lo esperas - Alex Rayón
El big data analytics donde menos te lo esperas - Alex RayónEl big data analytics donde menos te lo esperas - Alex Rayón
El big data analytics donde menos te lo esperas - Alex Rayón
 
Big Data en el sector inmobiliario - Gonzalo Martín
Big Data en el sector inmobiliario - Gonzalo MartínBig Data en el sector inmobiliario - Gonzalo Martín
Big Data en el sector inmobiliario - Gonzalo Martín
 
Modelo Operativo para grandes proyectos de AI - Ignacio Marrero
Modelo Operativo para grandes proyectos de AI - Ignacio MarreroModelo Operativo para grandes proyectos de AI - Ignacio Marrero
Modelo Operativo para grandes proyectos de AI - Ignacio Marrero
 
La evolución de la analítica descriptiva - Diego Aguirre
La evolución de la analítica descriptiva - Diego AguirreLa evolución de la analítica descriptiva - Diego Aguirre
La evolución de la analítica descriptiva - Diego Aguirre
 
El dato tiene forma y la forma significado - Josep Curto
El dato tiene forma y la forma significado - Josep CurtoEl dato tiene forma y la forma significado - Josep Curto
El dato tiene forma y la forma significado - Josep Curto
 
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentes
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentesBDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentes
BDAS-2017 | Evolución de Open Data en el desarrollo de las ciudades inteligentes
 
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos Digitales
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos DigitalesBDAS-2017 | Deep Learning para Extracción de Valor en Contenidos Digitales
BDAS-2017 | Deep Learning para Extracción de Valor en Contenidos Digitales
 
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...
BDAS-2017 | Maximizing a churn campaign’s profitability with cost sensitive m...
 
BDAS-2017 | sanselix jobranke_rpptx
BDAS-2017 | sanselix jobranke_rpptxBDAS-2017 | sanselix jobranke_rpptx
BDAS-2017 | sanselix jobranke_rpptx
 
BDAS-2017 | Analitica visual presentación mlms2
BDAS-2017 | Analitica visual presentación mlms2BDAS-2017 | Analitica visual presentación mlms2
BDAS-2017 | Analitica visual presentación mlms2
 
BDAS-2017 | Comunidad Data Science
BDAS-2017 | Comunidad Data ScienceBDAS-2017 | Comunidad Data Science
BDAS-2017 | Comunidad Data Science
 
BDAS-2017 | DMC Challengue concurso satisfacción universidad
BDAS-2017 | DMC Challengue concurso satisfacción universidadBDAS-2017 | DMC Challengue concurso satisfacción universidad
BDAS-2017 | DMC Challengue concurso satisfacción universidad
 
BDAS-2017 | Hanldling Target Bias in Predictive Modelling
BDAS-2017 | Hanldling Target Bias in Predictive ModellingBDAS-2017 | Hanldling Target Bias in Predictive Modelling
BDAS-2017 | Hanldling Target Bias in Predictive Modelling
 
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendencias
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendenciasBDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendencias
BDAS-2017 | Convergencia entre Open Data y Big Data, casos y tendencias
 
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...
BDAS-2017 | Big Bilbao: Big Data e Internet of Things para la promoción econó...
 
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big Data
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big DataBDAS-2017 | Comprendiendo nuestras motivaciones a través de Big Data
BDAS-2017 | Comprendiendo nuestras motivaciones a través de Big Data
 
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...
BDAS-2017 | Conozca la plataforma ideal para un procesamiento analítico sin p...
 
Building Innovative Data Products in a Banking Environment
Building Innovative Data Products in a Banking EnvironmentBuilding Innovative Data Products in a Banking Environment
Building Innovative Data Products in a Banking Environment
 

Dernier

Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxMohammedJunaid861692
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfRachmat Ramadhan H
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxolyaivanovalion
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxolyaivanovalion
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxolyaivanovalion
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxolyaivanovalion
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramMoniSankarHazra
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130Suhani Kapoor
 

Dernier (20)

Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Sampling (random) method and Non random.ppt
Sampling (random) method and Non random.pptSampling (random) method and Non random.ppt
Sampling (random) method and Non random.ppt
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdfMarket Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
Market Analysis in the 5 Largest Economic Countries in Southeast Asia.pdf
 
BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
Carero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptxCarero dropshipping via API with DroFx.pptx
Carero dropshipping via API with DroFx.pptx
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
 

TIMi: Faster predictions on big data with laptops

  • 1. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Big Data Modelos Predictivos Retos y generación de nuevas soluciones
  • 2. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 360 Customer View Connections without boundaries Incredible Speed and Reliability The promise…
  • 3. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 3 Cambie sus creencias! + preguntas, + modelos, + Citizen Data Scientists Menos Servidores, Mas Distributed Poweful Laptops - Hadoop, - Spark+, - CODIGO!
  • 4. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Part 1: Who are we?
  • 5. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Dr. Ir. Frank Vanden Berghen Phd. In Applied-Sciences with specialization in applied- mathematics (mathematical optimization) Building predictive models for more than 15 years, all around the world. Top winners at various world-level datamining competitions: 5
  • 6. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 6 Automation Moore’s Law Lifeofa Modelos Predictivos
  • 7. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 7 Objectives & Motivations
  • 8. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 8 At University IRIDIA=Research in Artificial Intelligence Neural Networks One Tree Forest of Trees
  • 9. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 9 In consulting… Far from AI… VS Now: Manual & Archaic (1 to 3 months to get 1 Model) Self-Learning & Auto-Adaptative Artificial Intelligence
  • 10. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 10 Market Reality: all is Scoring Quien? Que? X SELL UP SELL CHURN
  • 11. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Typical difficulties: • High Bayes-Error Levels • Small Target Size (<1%) • Scalability Issues • Before all: TIME! •AUTOMATED? 11 Churn, cross-sell, and up-sell models aren’t easy TIME! THERE IS NO TIME!
  • 12. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Inventsomething
  • 13. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Usual time to create one model for a datamining competition: 1 to 3 months 13 Ultimate Accuracy & No Free Lunch Competition Metric Winner TIMi (or similar automated tool) Difference Heritage Health Price Some kind of R² 46.12% 46.24% 0.12% AUSDM2009 (following Netflix) AUC 69.41% 69.24% 0.17% Kaggle Axa Telematics 2015 AUC 96.35% 95.97% 0.38% PAKDD2007 AUC 70.01% 69.28% 0.73% PAKDD2010* AUC 64.10% 63.30% 0.80% KDD2009-upselling AUC 90.92% 89.94% 0.98% Datascience.net Axacross-selling2015 Lift at 10% 26.09% 24.74% 1.35% KDD2009-churn AUC 76.51% 74.74% 1.77% KDD2009-appetency AUC 88.19% 86.31% 1.88% “No free lunch”: There will always exists a specific modeling algorithm that surpasses a “generic, general-purpose & automated tool” *: winning entry removed because it used additional external data and that’s cheating Look here
  • 14. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Sales A typical time-line for a SAS,IBM,R project: 14 Back in 2010 A typical time-line for a TIMi project: idea Data Preparation Model Total: 1 – 3 meses. Modelo: 2-6 weeks Total: 2 – 6 WEEKS. Modelo: 1-5 DAYSidea ETL MODEL CREATI VITY RUNTI ME Sales ETL MODEL CREATI VITY RUNTI ME Sales FUN
  • 15. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Part 2:Moore’s Law… …In real life
  • 16. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Moore’s Law: “The number of transistors that can be fit on a computer chip will double every two years, resulting in periodic increases in computing power.” 16 I despise Moore’s law!  FAST implementation, slow runtime  No attention to code quality  “Algorithmic complexity” ?  Efficient code = LOSING TIME Direct consequence of Moore’s Law:
  • 17. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 17 An observation: Moore’s Law is (somewhat) “broken” Source: “Computing Performance: Game Over or Next Level?” from Samuel H. Fuller, Analog Devices Inc. and Lynette I. Millett, National Research Council
  • 18. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 18 Moore’s Law is broken: …and it’s terrible! Exponential Growth of Data Volumes Technologies such as RFID and smartphones as well as the increasing use of social media application are resulting in a rapid rise in data volumes (Practically) No Growth in CPU speed Expectation Gap: factor of 10 Expectation Gap: factor of 1000 Expectation Gap: factor of 100
  • 19. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 19 Moore’s Law is broken: 2 Solutions • Low-Level Assembler & C code • Mathematical “tricks” • Algorithmic It’s the “seventies solution” • High-Level (i.e. slow) Language (i.e. Java & Spark) • Computing farm Supported by: • “Legacy” • Cloud services (Warning: Linear price-grid!) • Consulting Companies • Coders without any Assembler/C or algorithmic knowledge This is a possible solution if your wallet can grow exponentially with the size of your data. This will ultimately lead to high cost linked to legacy software.
  • 20. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 20 OPEN
  • 21. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Infrastructure Complexity Implementation (Time) Hadoop, Exadata and others cost hundreds of thousands of dollars Data mining requires PhD’s with years of experience in the field Implementing predictive models or complex KPI can take months or more to be integrated in the business processes Storage Data can be stored in a highly compressed file format that allows to store (and process) all the data from a 10 millions telecom for 3 years on one simple laptop Barriers to entry for “Big Data”
  • 22. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Complexity Do you need Phd in stats to answer analytical questions? (See also the concept of “Citizen Developer here: http://www.gartner.com/it-glossary/citizen- developer/ )
  • 23. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Complexity
  • 24. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. Deal with Big Data on a laptop: Live demo! 24 Scale of Solution
  • 25. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. On my laptop: • Compute a aggregate on a table with 17 columns and 1.3 billion rows: 70 seconds (finest granularity for 2 years of ticket data from a larger retailer with 1 million customer) • Sort a (CDR) table with 8 columns and 1 billion rows: 120 seconds. (finest granularity for 2 month of CDR data from a telecom with 5 millions subscribers) • Create 3 KDD-Grade-Predictive models (for churn, cross-sell, up-sell) on a learning dataset (from the KDD2009) with 50K rows and 15K columns (and than apply this model on the same scoring dataset): 20 minutes (about 7 minutes per model) The laptop has: Core i7 CPU at 2.4 GHz and a simple SSD drive. 25 Storage and computational Speed Live Demo! Conclusion: A simple laptop is enough to store & process all your data, whatever the size, the origin, the granularity, the type or the format of the data.
  • 26. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 26
  • 27. © 2016 Timi Americas S.A.S. – TIMi: Faster predictions, better decisions. 27 … to boldly go where no dataminer has bone before!