SlideShare une entreprise Scribd logo
1  sur  20
Télécharger pour lire hors ligne
Carrefour-Google Lab
Forecasting affluence in stores during lockdown
Chiara Biscaro
Senior Data Scientist
From stars to…. stores
2010-2014: PhD in Theoretical Physics at
University of Basel (CH)
2015-2016: Postdoc fellowship at Dark Cosmology
Centre, Copenhagen (DK)
From stars to…. stores
Aug 2016: S2DS
bootcamp, London
Nov 2016-2019:
Software Engineer
and Data Scientist at
Criteo, Paris (FR)
Welcome to the Carrefour-Google AI Lab!
2020 brought us an uninvited guest...
Credit: Leo Ortolani
Source
… with an international impact on the way people shop
Lockdown Italy
Lockdown France
… which created problems for our customers
Patrick Zagar Garnier
Chiara Biscaro
Anh Nguyen Van
Problem description: groceries during a lockdown
● To avoid queues (or at least manage them), we need our
supermarkets to know when the affluence is going to be
high
● Two predictions are useful:
a. Number of clients per day of week
b. Affluence (low/medium/high) for each hour of the day (8-20)
● Every Monday morning the store directors receive a
communication mail. Predictions for the entire week need
to be sent in order to communicate in a timely manner
Patrick Zagar Garnier
Chiara Biscaro
Anh Nguyen Van
Usual approach
Time series problem -> EASY! -> ARIMA/Prophet/XGBoost/RNNs….
… some caveats...
● Lack of data: at this point (beginning of April) we have ~3 weeks of data!!
● Lack of time: we need the model to be ready to send predictions on the field ASAP.
Different days of the week are now very similar to each other...
The life cycle of a (ML?) model
What if we
don’t use ML
here?
An “average” validation
Three models are considered:
1. Arithmetic average per hour/store
2. Arithmetic average per hour/day/store
3. Arithmetic average per hour/store with a double weight
on the day considered
With the following setup
● train period : 19 days
(2020-03-19 to 2020-04-09)
● validation period: 4 days
(2020-04-10 to 2020-04-15, excluding Easter Monday)
Forecast accuracy (FA) =
In production in one week, what it looks like
Monitor performance - Forecast accuracy per hour across time
70%
Let’s try some ML - Prophet
Forecast accuracy per day - Average vs Prophet
Let’s try some ML - Prophet
Forecast accuracy per hour for 15th April - Average vs Prophet
Limitations and next steps
● The model is too simple for the post-lockdown phase
● We are now working with Proximity stores to create a more powerful model for
prediction of affluence in post-lockdown conditions
70%
Conclusions
● Take a LOT of time talking to business people about what they need
and on which time scale
● Don’t over complicate simple requests with the risk of not delivering
● You need to know SOTA ML in order to know when NOT TO USE it
Credit: XKCD
xkcd.com/1838/
Thanks!

Contenu connexe

Similaire à In production in one week: forecasting affluence in supermarkets during lockdown by Chiara Biscaro, Senior Data Scientist @ Carrefour-Google AI Lab

Pablo García Montes - Product Manager | Product Owner | Scrum Coach
Pablo García Montes - Product Manager | Product Owner | Scrum CoachPablo García Montes - Product Manager | Product Owner | Scrum Coach
Pablo García Montes - Product Manager | Product Owner | Scrum CoachPablo García Montes
 
Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Albert Y. C. Chen
 
Supply chain process of Otobi.docx_3.pdf
Supply chain process of Otobi.docx_3.pdfSupply chain process of Otobi.docx_3.pdf
Supply chain process of Otobi.docx_3.pdfTopuKawser
 
Fantastic Problems and Where to Find Them: Daryl Weir
Fantastic Problems and Where to Find Them: Daryl WeirFantastic Problems and Where to Find Them: Daryl Weir
Fantastic Problems and Where to Find Them: Daryl WeirFuturice
 
BAQMaR - Conference Evening
BAQMaR - Conference EveningBAQMaR - Conference Evening
BAQMaR - Conference EveningBAQMaR
 
Cost of Delay, measurements and parallel vs. sequential project processing
Cost of Delay, measurements and parallel vs. sequential project processingCost of Delay, measurements and parallel vs. sequential project processing
Cost of Delay, measurements and parallel vs. sequential project processingSebastian Kamilli
 
Intro to Data Analytics with Oscar's Director of Product
 Intro to Data Analytics with Oscar's Director of Product Intro to Data Analytics with Oscar's Director of Product
Intro to Data Analytics with Oscar's Director of ProductProduct School
 
#TDCGlobal 2019, James Lovett, General Manager UK, Paack
#TDCGlobal 2019, James Lovett, General Manager UK, Paack#TDCGlobal 2019, James Lovett, General Manager UK, Paack
#TDCGlobal 2019, James Lovett, General Manager UK, PaackMetaPack
 
Sample Entrepreneurship Business plan for students
Sample Entrepreneurship Business plan for studentsSample Entrepreneurship Business plan for students
Sample Entrepreneurship Business plan for studentsChandrakanth M
 
How to frame a business challenge for innovation teams
How to frame a business challenge for innovation teamsHow to frame a business challenge for innovation teams
How to frame a business challenge for innovation teamsFranck Debane
 
Magui Mohamed Gadallah cv up
Magui Mohamed Gadallah cv upMagui Mohamed Gadallah cv up
Magui Mohamed Gadallah cv upMagui Gadallah
 
Lean advertising 101 - Paid Acquisition for Startups
Lean advertising 101 - Paid Acquisition for StartupsLean advertising 101 - Paid Acquisition for Startups
Lean advertising 101 - Paid Acquisition for StartupsClément Delangue
 
"What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual..."What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual...Dataconomy Media
 
Machine learning ~ Forecasting
Machine learning ~ ForecastingMachine learning ~ Forecasting
Machine learning ~ ForecastingShaswat Mandhanya
 
Modeling the Stock Market: Common pitfalls and how to avoid them!
Modeling the Stock Market: Common pitfalls and how to avoid them!Modeling the Stock Market: Common pitfalls and how to avoid them!
Modeling the Stock Market: Common pitfalls and how to avoid them!Jess Stauth
 
Playing Nice in the Product Playground
Playing Nice in the Product PlaygroundPlaying Nice in the Product Playground
Playing Nice in the Product PlaygroundIntuit Inc.
 
2020 Starts Tomorrow - Future Skills Profiles in the Media Industry
2020 Starts Tomorrow - Future Skills Profiles in the Media Industry2020 Starts Tomorrow - Future Skills Profiles in the Media Industry
2020 Starts Tomorrow - Future Skills Profiles in the Media IndustryIÐAN fræðslusetur
 
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Quantopian
 

Similaire à In production in one week: forecasting affluence in supermarkets during lockdown by Chiara Biscaro, Senior Data Scientist @ Carrefour-Google AI Lab (20)

Pablo García Montes - Product Manager | Product Owner | Scrum Coach
Pablo García Montes - Product Manager | Product Owner | Scrum CoachPablo García Montes - Product Manager | Product Owner | Scrum Coach
Pablo García Montes - Product Manager | Product Owner | Scrum Coach
 
Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0Making better use of Data and AI in Industry 4.0
Making better use of Data and AI in Industry 4.0
 
Supply chain process of Otobi.docx_3.pdf
Supply chain process of Otobi.docx_3.pdfSupply chain process of Otobi.docx_3.pdf
Supply chain process of Otobi.docx_3.pdf
 
Fantastic Problems and Where to Find Them: Daryl Weir
Fantastic Problems and Where to Find Them: Daryl WeirFantastic Problems and Where to Find Them: Daryl Weir
Fantastic Problems and Where to Find Them: Daryl Weir
 
BAQMaR - Conference Evening
BAQMaR - Conference EveningBAQMaR - Conference Evening
BAQMaR - Conference Evening
 
Cost of Delay, measurements and parallel vs. sequential project processing
Cost of Delay, measurements and parallel vs. sequential project processingCost of Delay, measurements and parallel vs. sequential project processing
Cost of Delay, measurements and parallel vs. sequential project processing
 
Mashnlearn case
Mashnlearn caseMashnlearn case
Mashnlearn case
 
Mrp cv
Mrp cvMrp cv
Mrp cv
 
Intro to Data Analytics with Oscar's Director of Product
 Intro to Data Analytics with Oscar's Director of Product Intro to Data Analytics with Oscar's Director of Product
Intro to Data Analytics with Oscar's Director of Product
 
#TDCGlobal 2019, James Lovett, General Manager UK, Paack
#TDCGlobal 2019, James Lovett, General Manager UK, Paack#TDCGlobal 2019, James Lovett, General Manager UK, Paack
#TDCGlobal 2019, James Lovett, General Manager UK, Paack
 
Sample Entrepreneurship Business plan for students
Sample Entrepreneurship Business plan for studentsSample Entrepreneurship Business plan for students
Sample Entrepreneurship Business plan for students
 
How to frame a business challenge for innovation teams
How to frame a business challenge for innovation teamsHow to frame a business challenge for innovation teams
How to frame a business challenge for innovation teams
 
Magui Mohamed Gadallah cv up
Magui Mohamed Gadallah cv upMagui Mohamed Gadallah cv up
Magui Mohamed Gadallah cv up
 
Lean advertising 101 - Paid Acquisition for Startups
Lean advertising 101 - Paid Acquisition for StartupsLean advertising 101 - Paid Acquisition for Startups
Lean advertising 101 - Paid Acquisition for Startups
 
"What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual..."What we learned from 5 years of building a data science software that actual...
"What we learned from 5 years of building a data science software that actual...
 
Machine learning ~ Forecasting
Machine learning ~ ForecastingMachine learning ~ Forecasting
Machine learning ~ Forecasting
 
Modeling the Stock Market: Common pitfalls and how to avoid them!
Modeling the Stock Market: Common pitfalls and how to avoid them!Modeling the Stock Market: Common pitfalls and how to avoid them!
Modeling the Stock Market: Common pitfalls and how to avoid them!
 
Playing Nice in the Product Playground
Playing Nice in the Product PlaygroundPlaying Nice in the Product Playground
Playing Nice in the Product Playground
 
2020 Starts Tomorrow - Future Skills Profiles in the Media Industry
2020 Starts Tomorrow - Future Skills Profiles in the Media Industry2020 Starts Tomorrow - Future Skills Profiles in the Media Industry
2020 Starts Tomorrow - Future Skills Profiles in the Media Industry
 
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
 

Plus de Paris Women in Machine Learning and Data Science

Plus de Paris Women in Machine Learning and Data Science (20)

Sequential and reinforcement learning for demand side management by Margaux B...
Sequential and reinforcement learning for demand side management by Margaux B...Sequential and reinforcement learning for demand side management by Margaux B...
Sequential and reinforcement learning for demand side management by Margaux B...
 
How and why AI should fight cybersexism, by Chloe Daudier
How and why AI should fight cybersexism, by Chloe DaudierHow and why AI should fight cybersexism, by Chloe Daudier
How and why AI should fight cybersexism, by Chloe Daudier
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Managing international tech teams, by Natasha Dimban
Managing international tech teams, by Natasha DimbanManaging international tech teams, by Natasha Dimban
Managing international tech teams, by Natasha Dimban
 
Optimizing GenAI apps, by N. El Mawass and Maria Knorps
Optimizing GenAI apps, by N. El Mawass and Maria KnorpsOptimizing GenAI apps, by N. El Mawass and Maria Knorps
Optimizing GenAI apps, by N. El Mawass and Maria Knorps
 
Perspectives, by M. Pannegeon
Perspectives, by M. PannegeonPerspectives, by M. Pannegeon
Perspectives, by M. Pannegeon
 
Evaluation strategies for dealing with partially labelled or unlabelled data
Evaluation strategies for dealing with partially labelled or unlabelled dataEvaluation strategies for dealing with partially labelled or unlabelled data
Evaluation strategies for dealing with partially labelled or unlabelled data
 
Combinatorial Optimisation with Policy Adaptation using latent Space Search, ...
Combinatorial Optimisation with Policy Adaptation using latent Space Search, ...Combinatorial Optimisation with Policy Adaptation using latent Space Search, ...
Combinatorial Optimisation with Policy Adaptation using latent Space Search, ...
 
An age-old question, by Caroline Jean-Pierre
An age-old question, by Caroline Jean-PierreAn age-old question, by Caroline Jean-Pierre
An age-old question, by Caroline Jean-Pierre
 
Applying Churn Prediction Approaches to the Telecom Industry, by Joëlle Lautré
Applying Churn Prediction Approaches to the Telecom Industry, by Joëlle LautréApplying Churn Prediction Approaches to the Telecom Industry, by Joëlle Lautré
Applying Churn Prediction Approaches to the Telecom Industry, by Joëlle Lautré
 
How to supervise a thesis in NLP in the ChatGPT era? By Laure Soulier
How to supervise a thesis in NLP in the ChatGPT era? By Laure SoulierHow to supervise a thesis in NLP in the ChatGPT era? By Laure Soulier
How to supervise a thesis in NLP in the ChatGPT era? By Laure Soulier
 
Global Ambitions Local Realities, by Anna Abreu
Global Ambitions Local Realities, by Anna AbreuGlobal Ambitions Local Realities, by Anna Abreu
Global Ambitions Local Realities, by Anna Abreu
 
Plug-and-Play methods for inverse problems in imagine, by Julie Delon
Plug-and-Play methods for inverse problems in imagine, by Julie DelonPlug-and-Play methods for inverse problems in imagine, by Julie Delon
Plug-and-Play methods for inverse problems in imagine, by Julie Delon
 
Sales Forecasting as a Data Product by Francesca Iannuzzi
Sales Forecasting as a Data Product by Francesca IannuzziSales Forecasting as a Data Product by Francesca Iannuzzi
Sales Forecasting as a Data Product by Francesca Iannuzzi
 
Identifying and mitigating bias in machine learning, by Ruta Binkyte
Identifying and mitigating bias in machine learning, by Ruta BinkyteIdentifying and mitigating bias in machine learning, by Ruta Binkyte
Identifying and mitigating bias in machine learning, by Ruta Binkyte
 
“Turning your ML algorithms into full web apps in no time with Python" by Mar...
“Turning your ML algorithms into full web apps in no time with Python" by Mar...“Turning your ML algorithms into full web apps in no time with Python" by Mar...
“Turning your ML algorithms into full web apps in no time with Python" by Mar...
 
Nature Language Processing for proteins by Amélie Héliou, Software Engineer @...
Nature Language Processing for proteins by Amélie Héliou, Software Engineer @...Nature Language Processing for proteins by Amélie Héliou, Software Engineer @...
Nature Language Processing for proteins by Amélie Héliou, Software Engineer @...
 
Sandrine Henry presents the BechdelAI project
Sandrine Henry presents the BechdelAI projectSandrine Henry presents the BechdelAI project
Sandrine Henry presents the BechdelAI project
 
Anastasiia Tryputen_War in Ukraine or how extraordinary courage reshapes geop...
Anastasiia Tryputen_War in Ukraine or how extraordinary courage reshapes geop...Anastasiia Tryputen_War in Ukraine or how extraordinary courage reshapes geop...
Anastasiia Tryputen_War in Ukraine or how extraordinary courage reshapes geop...
 
Khrystyna Grynko WiMLDS - From marketing to Tech.pdf
Khrystyna Grynko WiMLDS - From marketing to Tech.pdfKhrystyna Grynko WiMLDS - From marketing to Tech.pdf
Khrystyna Grynko WiMLDS - From marketing to Tech.pdf
 

Dernier

High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performancesivaprakash250
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Call Girls in Nagpur High Profile
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Dr.Costas Sachpazis
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...Call Girls in Nagpur High Profile
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Christo Ananth
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdfankushspencer015
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 

Dernier (20)

High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 

In production in one week: forecasting affluence in supermarkets during lockdown by Chiara Biscaro, Senior Data Scientist @ Carrefour-Google AI Lab

  • 1. Carrefour-Google Lab Forecasting affluence in stores during lockdown Chiara Biscaro Senior Data Scientist
  • 2. From stars to…. stores 2010-2014: PhD in Theoretical Physics at University of Basel (CH) 2015-2016: Postdoc fellowship at Dark Cosmology Centre, Copenhagen (DK)
  • 3. From stars to…. stores Aug 2016: S2DS bootcamp, London Nov 2016-2019: Software Engineer and Data Scientist at Criteo, Paris (FR)
  • 4. Welcome to the Carrefour-Google AI Lab!
  • 5. 2020 brought us an uninvited guest... Credit: Leo Ortolani Source
  • 6. … with an international impact on the way people shop Lockdown Italy Lockdown France
  • 7. … which created problems for our customers Patrick Zagar Garnier Chiara Biscaro Anh Nguyen Van
  • 8. Problem description: groceries during a lockdown ● To avoid queues (or at least manage them), we need our supermarkets to know when the affluence is going to be high ● Two predictions are useful: a. Number of clients per day of week b. Affluence (low/medium/high) for each hour of the day (8-20) ● Every Monday morning the store directors receive a communication mail. Predictions for the entire week need to be sent in order to communicate in a timely manner Patrick Zagar Garnier Chiara Biscaro Anh Nguyen Van
  • 9. Usual approach Time series problem -> EASY! -> ARIMA/Prophet/XGBoost/RNNs…. … some caveats... ● Lack of data: at this point (beginning of April) we have ~3 weeks of data!! ● Lack of time: we need the model to be ready to send predictions on the field ASAP.
  • 10. Different days of the week are now very similar to each other...
  • 11. The life cycle of a (ML?) model What if we don’t use ML here?
  • 12. An “average” validation Three models are considered: 1. Arithmetic average per hour/store 2. Arithmetic average per hour/day/store 3. Arithmetic average per hour/store with a double weight on the day considered With the following setup ● train period : 19 days (2020-03-19 to 2020-04-09) ● validation period: 4 days (2020-04-10 to 2020-04-15, excluding Easter Monday) Forecast accuracy (FA) =
  • 13. In production in one week, what it looks like
  • 14.
  • 15. Monitor performance - Forecast accuracy per hour across time 70%
  • 16. Let’s try some ML - Prophet Forecast accuracy per day - Average vs Prophet
  • 17. Let’s try some ML - Prophet Forecast accuracy per hour for 15th April - Average vs Prophet
  • 18. Limitations and next steps ● The model is too simple for the post-lockdown phase ● We are now working with Proximity stores to create a more powerful model for prediction of affluence in post-lockdown conditions 70%
  • 19. Conclusions ● Take a LOT of time talking to business people about what they need and on which time scale ● Don’t over complicate simple requests with the risk of not delivering ● You need to know SOTA ML in order to know when NOT TO USE it