SlideShare a Scribd company logo
1 of 19
Download to read offline
Global Heat Map &
Learning to Rank
Marco Catalano
Lead Engineer - Here Technologies
Data Driven Innovation – Rome 2018
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20182 © 2018 HERE Technologies
Agenda
01. Reverse Geocoder and
Global Heat Map
01.1 Reverse Geocoder
01.2 Extract data from the logs
01.3 Global Heat Map
02. Autocompletion and
Learning to Rank
02.1 Autocompletion
02.2 Learning to Rank
02.3 Continuos Ascending
Presentation title | Month 00, 20163 © 2016 HERE | HERE Internal Use Only
01
Reverse Geocoder and
Global Heat Map
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20184 © 2018 HERE Technologies
Reverse Geocoder
Reverse Geocoding is the process
of obtaining an address, an
administrative area or a known
landmark from a location in form
of its geocoordinates (Lat Lon)
The Reverse Geocoder is one of
HERE Technologies most heavily
used services and a huge amount
of data is produced by its access
logs
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20185 © 2018 HERE Technologies
What can we do with this information?
The basic consideration is that if a lot of reverse geocoder requests for a certain location are
present than there is a high likelihood that the location itself is to be considered a relevant one
defining a notion of relative place importance
The next step is therefore to count the reverse geocode probes in respect to some cellulation of
the earth
The earth is partitioned into cells
Defined by fixed latitude &
longitude increments
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20186 © 2018 HERE Technologies
Aggregate the Request Coordinates
Reverse geocodes within each cell are
summed and the values aggregated into
the bottom left corner of the respective
bounding box
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20187 © 2018 HERE Technologies
Problems and Limitations
India
Europe
Cells area vary by latitude and longitude
0,0001 degrees of latitude (4 digit
precision) equals to:
• Around 11 m at the equator
• Around 8 m at 67 (N/S)
Longitude and Elevation also introduce a
small error
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20188 © 2018 HERE Technologies
Visualize the data -> Global Heat Map
Heat map is a two dimensional visual representations of data.
The information, in the form of individual values, is contained
in a matrix and is represented using color gradients.
They are particularly useful where large volumes of data have
to be made comprehensible.
In digital image processing terms a heat map is a spatial
histogram, in other words the aggregation of histograms
computed for each and every earth cell.
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20189 © 2018 HERE Technologies
Visualize & Compare
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201810 © 2018 HERE Technologies
Visualize & Compare
San Francisco
2016 2014
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201811 © 2018 HERE Technologies
Visualize & Compare
Frankfurt am Main
2016 2014
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201812 © 2018 HERE Technologies
Visualize & Compare
Berlin
2016 2014
Presentation title | Month 00, 201613 © 2016 HERE | HERE Internal Use Only
02
Autocompletion and
Learning to Rank
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201814 © 2018 HERE Technologies
Auto Completion
Auto Completion allows end users to get good results with fewer keystrokes.
Use Cases
• Speed up typing
User starts typing and after a few characters a user interface provides a list of suggestions. The user selects what he’s interested in..
• User is unsure about spelling of an address
A user receives immediate feedback relative to input in form of suggestions and can complete or correct input quickly based on the suggestions.
• User is unsure about details of address
“via mazzini verona” suggests a complete address with all its details and can be completed to “Verona, Via Giuseppe Mazzini”
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201815 © 2018 HERE Technologies
Can we also use the relative place importance to improve our
autocompletion ranking model?
Information retrieval problem
Documents
D = { d1 , d 2 , ... , d N }
Query Q
Retrieval System
Ranked results
{ dq1 , dq2 , ... , dqN }
Tf-idf or BM25
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201816 © 2018 HERE Technologies
Learning to Rank information retrieval
Documents
D = { d1 , d 2 , ... , d n }
Query Q
Retrieval System
Ranked results
{ dq1 , dq2 , ... , dqn }
Learning Model
Training data
Q1{ dq1-1 , dq1-2 , ... , dq1-n }
Q2{ dq2-1 , dq2-2 , ... , dq2-n }
……..
Qm{ dqm-1 , dqm-2 , ... , dqm-n }
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201817 © 2018 HERE Technologies
How the Learning model works
f (d, q) -> v Feature
Array of computed features
[V1, V2, … Vn] -> Vf
Ranking function
g (Vf) -> Ranking score
Query-independent depend only on the document
Query-dependent depend on the document and on the
query
Query features depend only on the query
Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201818 © 2018 HERE Technologies
Coordinate Ascent
list-wise linear model which uses coordinate ascent to optimize
is an optimization that optimizes multivariate objective functions by
sequentially doing optimization in one dimension at a time. It cycles through
each parameter and optimizes over it while fixing all the others.
Why?
• It works well enough
• Linear therefore more predictable and human understandable
• Fast training process
Presentation title | Month 00, 201619 © 2016 HERE | HERE Internal Use Only
Thank you
Contact
Marco Catalano
Lead Engineer
HERE Technologies
Am Kronberger Hang 8
65824 Schwalbach
50° 9' 43" N. 8° 32' 1" E
Direct line: +4961965866540
marco.catalano@here.com
https://developer.here.com

More Related Content

Similar to Global Heat Map & Learning to Rank. Marco Catalano - HERE Technologies

DataOps: An Agile Method for Data-Driven Organizations
DataOps: An Agile Method for Data-Driven OrganizationsDataOps: An Agile Method for Data-Driven Organizations
DataOps: An Agile Method for Data-Driven OrganizationsEllen Friedman
 
State of the Map US 2018: Analytic Support to Mapping Contributors
State of the Map US 2018: Analytic Support to Mapping ContributorsState of the Map US 2018: Analytic Support to Mapping Contributors
State of the Map US 2018: Analytic Support to Mapping Contributorsrlewis48
 
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...Matt Stubbs
 
Digital Competence Framework for citizens (DigComp): State of play and Next S...
Digital Competence Framework for citizens (DigComp): State of play and Next S...Digital Competence Framework for citizens (DigComp): State of play and Next S...
Digital Competence Framework for citizens (DigComp): State of play and Next S...Riina Vuorikari
 
Smart Visualisations for IT & Enterprise Architecture Management with LeanIX
Smart Visualisations for IT & Enterprise Architecture Management with LeanIXSmart Visualisations for IT & Enterprise Architecture Management with LeanIX
Smart Visualisations for IT & Enterprise Architecture Management with LeanIXLeanIX GmbH
 
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...Craciun Elisei
 
Guest lecture impact business question on application landscape
Guest lecture impact business question on application landscapeGuest lecture impact business question on application landscape
Guest lecture impact business question on application landscapeLeon Smiers
 
7 Habits for Big Data in Production - keynote Big Data London Nov 2018
7 Habits for Big Data in Production - keynote Big Data London Nov 20187 Habits for Big Data in Production - keynote Big Data London Nov 2018
7 Habits for Big Data in Production - keynote Big Data London Nov 2018Ellen Friedman
 
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.02018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0Business Advantage
 
Cheryl Wiebe - Advanced Analytics in the Industrial World
Cheryl Wiebe - Advanced Analytics in the Industrial WorldCheryl Wiebe - Advanced Analytics in the Industrial World
Cheryl Wiebe - Advanced Analytics in the Industrial WorldRehgan Avon
 
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank Vogelezang
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank VogelezangBest Practices in Software Cost Estimation - Metrikon 2015 - Frank Vogelezang
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank VogelezangFrank Vogelezang
 
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14Jácome Cunha
 
Presentation of the WeGreenIT benchmark tool
Presentation of the WeGreenIT benchmark toolPresentation of the WeGreenIT benchmark tool
Presentation of the WeGreenIT benchmark toolICT FOOTPRINT .eu
 
Disadvantages Of Map Reduce
Disadvantages Of Map ReduceDisadvantages Of Map Reduce
Disadvantages Of Map ReduceKatrina Green
 
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...Matt Stubbs
 
Where is Data Going? - RMDC Keynote
Where is Data Going? - RMDC KeynoteWhere is Data Going? - RMDC Keynote
Where is Data Going? - RMDC KeynoteTed Dunning
 
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...NRB
 
Analyze your application portfolio to know where the quality and risk issues ...
Analyze your application portfolio to know where the quality and risk issues ...Analyze your application portfolio to know where the quality and risk issues ...
Analyze your application portfolio to know where the quality and risk issues ...Sogeti Nederland B.V.
 
Le Bourget 2017 - From earth observation to actionable intelligence
Le Bourget 2017 - From earth observation to actionable intelligenceLe Bourget 2017 - From earth observation to actionable intelligence
Le Bourget 2017 - From earth observation to actionable intelligenceLeonardo
 

Similar to Global Heat Map & Learning to Rank. Marco Catalano - HERE Technologies (20)

DataOps: An Agile Method for Data-Driven Organizations
DataOps: An Agile Method for Data-Driven OrganizationsDataOps: An Agile Method for Data-Driven Organizations
DataOps: An Agile Method for Data-Driven Organizations
 
State of the Map US 2018: Analytic Support to Mapping Contributors
State of the Map US 2018: Analytic Support to Mapping ContributorsState of the Map US 2018: Analytic Support to Mapping Contributors
State of the Map US 2018: Analytic Support to Mapping Contributors
 
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...
Big Data LDN 2018: 7 SUCCESSFUL HABITS FOR DATA-INTENSIVE APPLICATIONS IN PRO...
 
Digital Competence Framework for citizens (DigComp): State of play and Next S...
Digital Competence Framework for citizens (DigComp): State of play and Next S...Digital Competence Framework for citizens (DigComp): State of play and Next S...
Digital Competence Framework for citizens (DigComp): State of play and Next S...
 
Smart Visualisations for IT & Enterprise Architecture Management with LeanIX
Smart Visualisations for IT & Enterprise Architecture Management with LeanIXSmart Visualisations for IT & Enterprise Architecture Management with LeanIX
Smart Visualisations for IT & Enterprise Architecture Management with LeanIX
 
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...
INTEGRATED MONITORING SYSTEM REDUCES INTERNAL FUEL CONSUMPTION WITH 12% FOR O...
 
Guest lecture impact business question on application landscape
Guest lecture impact business question on application landscapeGuest lecture impact business question on application landscape
Guest lecture impact business question on application landscape
 
7 Habits for Big Data in Production - keynote Big Data London Nov 2018
7 Habits for Big Data in Production - keynote Big Data London Nov 20187 Habits for Big Data in Production - keynote Big Data London Nov 2018
7 Habits for Big Data in Production - keynote Big Data London Nov 2018
 
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.02018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
2018/2019 Global CAD Trends Survey Report - by Business Advantage v3.0
 
Cheryl Wiebe - Advanced Analytics in the Industrial World
Cheryl Wiebe - Advanced Analytics in the Industrial WorldCheryl Wiebe - Advanced Analytics in the Industrial World
Cheryl Wiebe - Advanced Analytics in the Industrial World
 
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank Vogelezang
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank VogelezangBest Practices in Software Cost Estimation - Metrikon 2015 - Frank Vogelezang
Best Practices in Software Cost Estimation - Metrikon 2015 - Frank Vogelezang
 
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14
Spreadsheet Engineering @ OSU - EECS Colloquium - 02/24/14
 
Presentation of the WeGreenIT benchmark tool
Presentation of the WeGreenIT benchmark toolPresentation of the WeGreenIT benchmark tool
Presentation of the WeGreenIT benchmark tool
 
Disadvantages Of Map Reduce
Disadvantages Of Map ReduceDisadvantages Of Map Reduce
Disadvantages Of Map Reduce
 
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...
Big Data LDN 2018: DATA OPERATIONS PROBLEMS CREATED BY DEEP LEARNING, AND HOW...
 
iSAC6+ | An unique citizen attention service
iSAC6+ | An unique citizen attention serviceiSAC6+ | An unique citizen attention service
iSAC6+ | An unique citizen attention service
 
Where is Data Going? - RMDC Keynote
Where is Data Going? - RMDC KeynoteWhere is Data Going? - RMDC Keynote
Where is Data Going? - RMDC Keynote
 
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...
NRB MAINFRAME DAY 02 - Gamal Khaldi - NRB Mainframe YtD recap and outlook 201...
 
Analyze your application portfolio to know where the quality and risk issues ...
Analyze your application portfolio to know where the quality and risk issues ...Analyze your application portfolio to know where the quality and risk issues ...
Analyze your application portfolio to know where the quality and risk issues ...
 
Le Bourget 2017 - From earth observation to actionable intelligence
Le Bourget 2017 - From earth observation to actionable intelligenceLe Bourget 2017 - From earth observation to actionable intelligence
Le Bourget 2017 - From earth observation to actionable intelligence
 

More from Data Driven Innovation

Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...Data Driven Innovation
 
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...Data Driven Innovation
 
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...Data Driven Innovation
 
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...Data Driven Innovation
 
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...Data Driven Innovation
 
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)Data Driven Innovation
 
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...Data Driven Innovation
 
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...Data Driven Innovation
 
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...Data Driven Innovation
 
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...Data Driven Innovation
 
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)Data Driven Innovation
 
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...Data Driven Innovation
 
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)Data Driven Innovation
 
Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...Data Driven Innovation
 
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...Data Driven Innovation
 
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...Data Driven Innovation
 
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...Data Driven Innovation
 
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)Data Driven Innovation
 
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)Data Driven Innovation
 
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...Data Driven Innovation
 

More from Data Driven Innovation (20)

Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
Integrazione della mobilità elettrica nei sistemi urbani (Stefano Carrese, Un...
 
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
La statistica ufficiale e i trasporti marittimi nell'era dei big data (Vincen...
 
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
How can we realize the Mobility as a Service (Maas) (Andrea Paletti, London S...
 
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
Il DTC-Lazio e i dati del patrimonio culturale (Maria Prezioso, Università To...
 
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
CHNet-DHLab: Servizi Cloud a supporto dei beni culturali (Fabio Proietti, INF...
 
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
Progetto EOSC-Pillar (Fulvio Galeazzi, GARR)
 
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
Una infrastruttura per l’accesso al patrimonio culturale: il Progetto del Por...
 
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
Utilizzo dei Big data per l’analisi dei flussi veicolari e della mobilità (Ma...
 
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
I dati personali nell'analisi comportamentale della mobilità di dipendenti e ...
 
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
Estrarre valore dai dati: tecnologie per ottimizzare la mobilità del futuro (...
 
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
Le piattaforme dati per la mobilità nelle città italiane (Marco Mena, EY)
 
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
WiseTown, un ecosistema di applicazioni e strumenti per migliorare la qualità...
 
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
CityOpenSource as a civic tech tool (Ilaria Vitellio, CityOpenSource)
 
Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...Big Data Confederation: toward the local urban data market place (Renzo Taffa...
Big Data Confederation: toward the local urban data market place (Renzo Taffa...
 
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
Making citizens the eyes of policy makers: a sweet spot for hybrid AI? (Danie...
 
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
Dall'Agenda Digitale alla Smart City: il percorso di Roma Capitale verso il D...
 
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
Reusing open data: how to make a difference (Vittorio Scarano, Università di ...
 
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
Gestire i beni culturali con i big data (Sandro Stancampiano, Istat)
 
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
Data Governance: cos’è e perché è importante? (Elena Arista, Erwin)
 
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
Data driven economy: bastano i dati per avviare una start up? (Gabriele Anton...
 

Recently uploaded

The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerPavel Šabatka
 
Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Vladislav Solodkiy
 
ChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics InfrastructureChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics Infrastructuresonikadigital1
 
How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?sonikadigital1
 
5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best PracticesDataArchiva
 
CI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionCI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionajayrajaganeshkayala
 
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxTINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxDwiAyuSitiHartinah
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introductionsanjaymuralee1
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Guido X Jansen
 
Optimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsOptimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsThinkInnovation
 
Master's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationMaster's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationGiorgio Carbone
 
Mapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxMapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxVenkatasubramani13
 
Rock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxRock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxFinatron037
 
Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...PrithaVashisht1
 
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxCCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxdhiyaneswaranv1
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityAggregage
 

Recently uploaded (16)

The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayer
 
Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023Cash Is Still King: ATM market research '2023
Cash Is Still King: ATM market research '2023
 
ChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics InfrastructureChistaDATA Real-Time DATA Analytics Infrastructure
ChistaDATA Real-Time DATA Analytics Infrastructure
 
How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?How is Real-Time Analytics Different from Traditional OLAP?
How is Real-Time Analytics Different from Traditional OLAP?
 
5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices5 Ds to Define Data Archiving Best Practices
5 Ds to Define Data Archiving Best Practices
 
CI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual interventionCI, CD -Tools to integrate without manual intervention
CI, CD -Tools to integrate without manual intervention
 
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptxTINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
TINJUAN PEMROSESAN TRANSAKSI DAN ERP.pptx
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introduction
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
 
Optimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsOptimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in Logistics
 
Master's Thesis - Data Science - Presentation
Master's Thesis - Data Science - PresentationMaster's Thesis - Data Science - Presentation
Master's Thesis - Data Science - Presentation
 
Mapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptxMapping the pubmed data under different suptopics using NLP.pptx
Mapping the pubmed data under different suptopics using NLP.pptx
 
Rock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxRock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptx
 
Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...
 
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxCCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
 

Global Heat Map & Learning to Rank. Marco Catalano - HERE Technologies

  • 1. Global Heat Map & Learning to Rank Marco Catalano Lead Engineer - Here Technologies Data Driven Innovation – Rome 2018
  • 2. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20182 © 2018 HERE Technologies Agenda 01. Reverse Geocoder and Global Heat Map 01.1 Reverse Geocoder 01.2 Extract data from the logs 01.3 Global Heat Map 02. Autocompletion and Learning to Rank 02.1 Autocompletion 02.2 Learning to Rank 02.3 Continuos Ascending
  • 3. Presentation title | Month 00, 20163 © 2016 HERE | HERE Internal Use Only 01 Reverse Geocoder and Global Heat Map
  • 4. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20184 © 2018 HERE Technologies Reverse Geocoder Reverse Geocoding is the process of obtaining an address, an administrative area or a known landmark from a location in form of its geocoordinates (Lat Lon) The Reverse Geocoder is one of HERE Technologies most heavily used services and a huge amount of data is produced by its access logs
  • 5. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20185 © 2018 HERE Technologies What can we do with this information? The basic consideration is that if a lot of reverse geocoder requests for a certain location are present than there is a high likelihood that the location itself is to be considered a relevant one defining a notion of relative place importance The next step is therefore to count the reverse geocode probes in respect to some cellulation of the earth The earth is partitioned into cells Defined by fixed latitude & longitude increments
  • 6. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20186 © 2018 HERE Technologies Aggregate the Request Coordinates Reverse geocodes within each cell are summed and the values aggregated into the bottom left corner of the respective bounding box
  • 7. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20187 © 2018 HERE Technologies Problems and Limitations India Europe Cells area vary by latitude and longitude 0,0001 degrees of latitude (4 digit precision) equals to: • Around 11 m at the equator • Around 8 m at 67 (N/S) Longitude and Elevation also introduce a small error
  • 8. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20188 © 2018 HERE Technologies Visualize the data -> Global Heat Map Heat map is a two dimensional visual representations of data. The information, in the form of individual values, is contained in a matrix and is represented using color gradients. They are particularly useful where large volumes of data have to be made comprehensible. In digital image processing terms a heat map is a spatial histogram, in other words the aggregation of histograms computed for each and every earth cell.
  • 9. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 20189 © 2018 HERE Technologies Visualize & Compare
  • 10. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201810 © 2018 HERE Technologies Visualize & Compare San Francisco 2016 2014
  • 11. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201811 © 2018 HERE Technologies Visualize & Compare Frankfurt am Main 2016 2014
  • 12. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201812 © 2018 HERE Technologies Visualize & Compare Berlin 2016 2014
  • 13. Presentation title | Month 00, 201613 © 2016 HERE | HERE Internal Use Only 02 Autocompletion and Learning to Rank
  • 14. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201814 © 2018 HERE Technologies Auto Completion Auto Completion allows end users to get good results with fewer keystrokes. Use Cases • Speed up typing User starts typing and after a few characters a user interface provides a list of suggestions. The user selects what he’s interested in.. • User is unsure about spelling of an address A user receives immediate feedback relative to input in form of suggestions and can complete or correct input quickly based on the suggestions. • User is unsure about details of address “via mazzini verona” suggests a complete address with all its details and can be completed to “Verona, Via Giuseppe Mazzini”
  • 15. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201815 © 2018 HERE Technologies Can we also use the relative place importance to improve our autocompletion ranking model? Information retrieval problem Documents D = { d1 , d 2 , ... , d N } Query Q Retrieval System Ranked results { dq1 , dq2 , ... , dqN } Tf-idf or BM25
  • 16. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201816 © 2018 HERE Technologies Learning to Rank information retrieval Documents D = { d1 , d 2 , ... , d n } Query Q Retrieval System Ranked results { dq1 , dq2 , ... , dqn } Learning Model Training data Q1{ dq1-1 , dq1-2 , ... , dq1-n } Q2{ dq2-1 , dq2-2 , ... , dq2-n } …….. Qm{ dqm-1 , dqm-2 , ... , dqm-n }
  • 17. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201817 © 2018 HERE Technologies How the Learning model works f (d, q) -> v Feature Array of computed features [V1, V2, … Vn] -> Vf Ranking function g (Vf) -> Ranking score Query-independent depend only on the document Query-dependent depend on the document and on the query Query features depend only on the query
  • 18. Global Heat Map & Learning to Rank | Data Driven Innovation – Rome 201818 © 2018 HERE Technologies Coordinate Ascent list-wise linear model which uses coordinate ascent to optimize is an optimization that optimizes multivariate objective functions by sequentially doing optimization in one dimension at a time. It cycles through each parameter and optimizes over it while fixing all the others. Why? • It works well enough • Linear therefore more predictable and human understandable • Fast training process
  • 19. Presentation title | Month 00, 201619 © 2016 HERE | HERE Internal Use Only Thank you Contact Marco Catalano Lead Engineer HERE Technologies Am Kronberger Hang 8 65824 Schwalbach 50° 9' 43" N. 8° 32' 1" E Direct line: +4961965866540 marco.catalano@here.com https://developer.here.com