SlideShare a Scribd company logo
1 of 37
Download to read offline
AI at 7shifts
How we use data to increase the value
of our restaurant scheduling system
Logan Kopas
Pronouns: He/Him
Introduction
Who I am
Logan Kopas
Data Team Lead
A little about me
I started out working as a full stack developer at NC
Smart Call. I went back to school to do my masters
in bioinformatics and deep learning. During my
masters I began working at 7shifts and I’m loving it.
I get to combine everything I’ve learned from
undergrad, working at NC Smart Call, and my
masters, as well as learn new skills and face new
challenges. Additionally, I started a data science
consulting company with Conor Lazarou to help
other companies get started with data and
analytics.
Undergrad
NC Smart Call
Grad School
7shifts
Introduction
Who I am
Introduction
7shifts
Who we are
7shifts
● ~160 employees
● Offices in Saskatoon,
Toronto, and New York
● VC Funded
● Rapidly growing (except for
covid)
What we do
● Employee management for
restaurants
○ Scheduling
○ Labour and POS
integrations
○ Time tracking
○ Plus more
Data at 7shifts
Where we’re at
Est. July 2019
Data Science Data Analysis
Data Scientist
ML expert
Data Warehouse
Developer
Data storage and
distribution
Data Analyst
Most data science-y analyst
Data Analyst
Tableau expert
Data Team Lead
No special skills
Conor Tolo Will Kiara
Data
Developer
Data Pipelines
Jessie
Data
First things first,
build a data
warehouse
Technology
- Apache beam (python)
- Postgres
- Ansible
- That’s it.
Building a data warehouse
Hosting
- Compute Engine VM
- Persistent Disk Storage
Building a data warehouse
Infrastructure
Building a data warehouse
Pipelines
Storing data is only partially
useful.
- We need to get the data to our 3rd party tools
so that our teammates can use it
Building a data warehouse
Pipelines
Problem
- Intercom wants info on “users” and “companies”
- Salesforce wants info on “leads”,
“opportunities”, “accounts”, and “contacts”
Building a data warehouse
Pipelines
Solution
- Push all events into Roughneck
- Perform nightly update through Roughneck as
well
Event A
● User ID
● Company ID
● Event name
Enrich from DB
● Lead ID
● Intercom ID
● Account Owner
● Etc.
●
Salesforce
Intercom
Convert
● Proper fields and
formatting for each
destination
Events are a large part of our
incoming data.
- Currently we dump it all into a data swamp
- We also pipe the clean stuff into Amplitude
- We have plans for an event warehouse
Building a data warehouse
Events
Event Warehouse Hopes and
Dreams
- Graph database
- Great for questions like
- How many steps do users take from starting
to build a schedule to publishing it?
- What are the most common paths that arrive
on the billing page?
Building a data warehouse
Events
https://snowplowanalytics.com/blog/2018/03/26/building-a-model-for-atomic-event-data-as-a-graph/
session_start
view_home_p
age
publish_
schedule
User X
User Y
User A
for
next next
notify
notify
AI for internal use
PoP Model - Probability of
Paying
- Tracks company stats as they go through trial
- Score from 0-1
- Allows sales to focus on customers that need an
extra nudge
- Indicator of Marketing lead quality
AI for internal use
PoP Model
PoP Model - v1
- Random Forest
- Based on different events and properties
- Integrated POS system
- Input employees birthdays
- Published schedule
- Employee logins
AI for internal use
PoP Model
PoP Model - v2
- XGBoost
- Incorporates events at different times in the trial
- Number of employee logins in week 1
- Days to first published schedule
AI for internal use
PoP Model
Section heading
Page heading
Other internal AI tools
● Plan suggestion model*
● Upsell suggestion model*
● Customer churn prediction model*
*All under development
Photo by NeONBRAND on Unsplash
"Man, this shit makes my job so easy"
Sales person
"I was calling laundromats and nail salons,
PoP saves my life, I actually call
restaurants now"
Sales person
Photo by Rachel Park on Unsplash
AI as a product
Employee Engagement Score
● Tracks employee engagement
● Can be an early indicator of churn
or other issues
AI as a product
Intro
Autoscheduler
● Generates a schedule
automatically
○ Based on predicted sales,
optimal labour, previous
employee schedules,
events, etc.
AI as a product
Autoscheduler
Autoscheduler recipe
● Dash of Sales Forecasting
● 1 part LabourNet
● 1 part ShiftMaker
● 1 part ShiftFiller
● Rinse glass with dash of sales forecasting
● Blend LabourNet and ShiftMaker together,
strain into glass
● Sprinkle ShiftFiller on top
● Garnish and serve
Photo by Mgg Vitchakorn on Unsplash
Autoscheduler
Sales Forecasting
Autoscheduler
Sales Forecasting
Sales Forecasting Ensemble
● Ensemble model combining 3 different sales forecasting algorithms
○ Short, medium, and long term forecasting models
Autoscheduler
LabourNet
Autoscheduler
LabourNet
Deep Learning
● Tensorflow/Keras neural network with 1D-convolutional architecture
● Outputs optimal number of workers for each role throughout the day
Autoscheduler
ShiftMaker
Autoscheduler
ShiftMaker
Shift
● Creates shifts to meet the
labour demand curve
● Adheres to restaurant rules
such as: min/max shift length,
start/end time, etc.
● Also splits, combines, expands,
trims, and adjusts shifts to
meet requirements
Autoscheduler
ShiftFiller
Autoscheduler
ShiftFiller
ShiftFiller
● Traditional AI that assigns employees to shifts
○ Heuristically solves the “nurse scheduling problem”
● Adheres to hard rules
○ Only 1 employee per shift, only roles the employee is assigned to,
weekly OT thresholds
● Maximizes score based on soft rules
○ Common working times/days, target hours
● Stochastic hill climbing
Questions?
7shifts.com/careers / flatland.AI
logan.kopas@7shifts.com / logan@flatland.ai
LinkedIn: Logan Kopas
Twitter: @logankopas

More Related Content

What's hot

North Star metrics and OKRs to show DevRel value and get focus
North Star metrics and OKRs to show DevRel value and get focusNorth Star metrics and OKRs to show DevRel value and get focus
North Star metrics and OKRs to show DevRel value and get focusVera Tiago
 
Reimagining Your Higher Ed Web Strategy
Reimagining Your Higher Ed Web StrategyReimagining Your Higher Ed Web Strategy
Reimagining Your Higher Ed Web StrategyMediacurrent
 
Improving the Results You Get From Analytics
Improving the Results You Get From AnalyticsImproving the Results You Get From Analytics
Improving the Results You Get From AnalyticsPhil Kelly
 
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)Tech in Asia ID
 
7 Secrets of Successful Performance Appraisals
7 Secrets of Successful Performance Appraisals7 Secrets of Successful Performance Appraisals
7 Secrets of Successful Performance AppraisalsMelissa_BizMerlin
 
Become an SEO expert by experimentation
Become an SEO expert by experimentationBecome an SEO expert by experimentation
Become an SEO expert by experimentationEli Schwartz
 
Design studio-method-industry2016 (1)
Design studio-method-industry2016 (1)Design studio-method-industry2016 (1)
Design studio-method-industry2016 (1)LeanDog
 
Using flow based road mapping and options
Using flow based road mapping and optionsUsing flow based road mapping and options
Using flow based road mapping and optionsLeanDog
 
#18ntc capacity is more than a buzzword
#18ntc capacity is more than a buzzword#18ntc capacity is more than a buzzword
#18ntc capacity is more than a buzzwordSteve Heye
 
Managing The Chaos of Work
Managing The Chaos of Work Managing The Chaos of Work
Managing The Chaos of Work Planview
 
Setting Product Development Priorities
Setting Product Development Priorities Setting Product Development Priorities
Setting Product Development Priorities Kendra Skeene
 
Growth hacking ID presentation
Growth hacking ID presentationGrowth hacking ID presentation
Growth hacking ID presentationPhilip Oedi
 
[Panel] Convincing Your Company to Improve Your Technical Resource Center
[Panel] Convincing Your Company to Improve Your Technical Resource Center[Panel] Convincing Your Company to Improve Your Technical Resource Center
[Panel] Convincing Your Company to Improve Your Technical Resource CenterInformation Development World
 
Speeding up front-line customer service
Speeding up front-line customer serviceSpeeding up front-line customer service
Speeding up front-line customer serviceContent Strategy Inc.
 
Translating Strategy into Action with Enterprise Architecture Webinar
Translating Strategy into Action with Enterprise Architecture WebinarTranslating Strategy into Action with Enterprise Architecture Webinar
Translating Strategy into Action with Enterprise Architecture WebinarPlanview
 
Go Weekly Sprints
Go Weekly SprintsGo Weekly Sprints
Go Weekly SprintsGo Weekly
 
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...Bridging the Gap Between Data Science & Engineer: Building High-Performance T...
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...ryanorban
 
The Truth About Growth Hacking in B2B
The Truth About Growth Hacking in B2BThe Truth About Growth Hacking in B2B
The Truth About Growth Hacking in B2BVishal Sunak
 
Maximize Project 2010 with Office 365 for Project Management Success
Maximize Project 2010 with Office 365 for Project Management SuccessMaximize Project 2010 with Office 365 for Project Management Success
Maximize Project 2010 with Office 365 for Project Management SuccessDux Raymond Sy
 

What's hot (20)

North Star metrics and OKRs to show DevRel value and get focus
North Star metrics and OKRs to show DevRel value and get focusNorth Star metrics and OKRs to show DevRel value and get focus
North Star metrics and OKRs to show DevRel value and get focus
 
Reimagining Your Higher Ed Web Strategy
Reimagining Your Higher Ed Web StrategyReimagining Your Higher Ed Web Strategy
Reimagining Your Higher Ed Web Strategy
 
Improving the Results You Get From Analytics
Improving the Results You Get From AnalyticsImproving the Results You Get From Analytics
Improving the Results You Get From Analytics
 
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)
"How To Build and Lead a Winning Data Team" by Cahyo Listyanto (Bizzy.co.id)
 
7 Secrets of Successful Performance Appraisals
7 Secrets of Successful Performance Appraisals7 Secrets of Successful Performance Appraisals
7 Secrets of Successful Performance Appraisals
 
Become an SEO expert by experimentation
Become an SEO expert by experimentationBecome an SEO expert by experimentation
Become an SEO expert by experimentation
 
Design studio-method-industry2016 (1)
Design studio-method-industry2016 (1)Design studio-method-industry2016 (1)
Design studio-method-industry2016 (1)
 
Using flow based road mapping and options
Using flow based road mapping and optionsUsing flow based road mapping and options
Using flow based road mapping and options
 
#18ntc capacity is more than a buzzword
#18ntc capacity is more than a buzzword#18ntc capacity is more than a buzzword
#18ntc capacity is more than a buzzword
 
Managing The Chaos of Work
Managing The Chaos of Work Managing The Chaos of Work
Managing The Chaos of Work
 
Setting Product Development Priorities
Setting Product Development Priorities Setting Product Development Priorities
Setting Product Development Priorities
 
Growth hacking ID presentation
Growth hacking ID presentationGrowth hacking ID presentation
Growth hacking ID presentation
 
[Panel] Convincing Your Company to Improve Your Technical Resource Center
[Panel] Convincing Your Company to Improve Your Technical Resource Center[Panel] Convincing Your Company to Improve Your Technical Resource Center
[Panel] Convincing Your Company to Improve Your Technical Resource Center
 
Speeding up front-line customer service
Speeding up front-line customer serviceSpeeding up front-line customer service
Speeding up front-line customer service
 
Translating Strategy into Action with Enterprise Architecture Webinar
Translating Strategy into Action with Enterprise Architecture WebinarTranslating Strategy into Action with Enterprise Architecture Webinar
Translating Strategy into Action with Enterprise Architecture Webinar
 
Go Weekly Sprints
Go Weekly SprintsGo Weekly Sprints
Go Weekly Sprints
 
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...Bridging the Gap Between Data Science & Engineer: Building High-Performance T...
Bridging the Gap Between Data Science & Engineer: Building High-Performance T...
 
The Truth About Growth Hacking in B2B
The Truth About Growth Hacking in B2BThe Truth About Growth Hacking in B2B
The Truth About Growth Hacking in B2B
 
Maximize Project 2010 with Office 365 for Project Management Success
Maximize Project 2010 with Office 365 for Project Management SuccessMaximize Project 2010 with Office 365 for Project Management Success
Maximize Project 2010 with Office 365 for Project Management Success
 
Technical project management
Technical project managementTechnical project management
Technical project management
 

Similar to Data for Good Regina - 7shifts Presentation

AppDynamics User Group
AppDynamics User GroupAppDynamics User Group
AppDynamics User GroupMike Ruangutai
 
Architecting for analytics
Architecting for analyticsArchitecting for analytics
Architecting for analyticsRob Winters
 
How to become Data Driven for startups - keboola
How to become Data Driven for startups - keboolaHow to become Data Driven for startups - keboola
How to become Data Driven for startups - keboolaPavel Dolezal
 
The Bumpy Road to Actionable SLOs
The Bumpy Road to Actionable SLOsThe Bumpy Road to Actionable SLOs
The Bumpy Road to Actionable SLOsDevOps.com
 
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...Hannah Flynn
 
How and Why: Embedded Analytics Interfaces For Your SaaS Product
How and Why: Embedded Analytics Interfaces For Your SaaS ProductHow and Why: Embedded Analytics Interfaces For Your SaaS Product
How and Why: Embedded Analytics Interfaces For Your SaaS ProductAggregage
 
Data_and_Analytics_Industry_IESE_v3.pdf
Data_and_Analytics_Industry_IESE_v3.pdfData_and_Analytics_Industry_IESE_v3.pdf
Data_and_Analytics_Industry_IESE_v3.pdfprevota
 
How Gousto is moving to just-in-time personalization with Snowplow
How Gousto is moving to just-in-time personalization with SnowplowHow Gousto is moving to just-in-time personalization with Snowplow
How Gousto is moving to just-in-time personalization with SnowplowGiuseppe Gaviani
 
SOP Planning and Optimization Solution-as-a-Service.pdf
SOP Planning and Optimization Solution-as-a-Service.pdfSOP Planning and Optimization Solution-as-a-Service.pdf
SOP Planning and Optimization Solution-as-a-Service.pdfDavid Barbieri Kennedy
 
Superweek2019 dmo presentation
Superweek2019 dmo presentationSuperweek2019 dmo presentation
Superweek2019 dmo presentationDanny Mawani Olsen
 
Better Living Through Analytics - Louis Cialdella Product School
Better Living Through Analytics - Louis Cialdella Product SchoolBetter Living Through Analytics - Louis Cialdella Product School
Better Living Through Analytics - Louis Cialdella Product SchoolLouis Cialdella
 
Operationalizing Data Science: The Right Architecture and Tools
Operationalizing Data Science: The Right Architecture and ToolsOperationalizing Data Science: The Right Architecture and Tools
Operationalizing Data Science: The Right Architecture and ToolsVMware Tanzu
 
Data Con LA 2019 - The challenges of data science for veteran media organizat...
Data Con LA 2019 - The challenges of data science for veteran media organizat...Data Con LA 2019 - The challenges of data science for veteran media organizat...
Data Con LA 2019 - The challenges of data science for veteran media organizat...Data Con LA
 
Gentile Consulting
Gentile ConsultingGentile Consulting
Gentile Consultingcgentile
 
Working with data.pdf
Working with data.pdfWorking with data.pdf
Working with data.pdfBJZarate
 
Aligning Feature Delivery with OKRs by Gtmhub CPO
Aligning Feature Delivery with OKRs by Gtmhub CPOAligning Feature Delivery with OKRs by Gtmhub CPO
Aligning Feature Delivery with OKRs by Gtmhub CPOProduct School
 
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...Workday, Inc.
 
Help Me, Help You: Supporting Your Data
Help Me, Help You: Supporting Your DataHelp Me, Help You: Supporting Your Data
Help Me, Help You: Supporting Your DataData Con LA
 

Similar to Data for Good Regina - 7shifts Presentation (20)

AppDynamics User Group
AppDynamics User GroupAppDynamics User Group
AppDynamics User Group
 
Architecting for analytics
Architecting for analyticsArchitecting for analytics
Architecting for analytics
 
How to become Data Driven for startups - keboola
How to become Data Driven for startups - keboolaHow to become Data Driven for startups - keboola
How to become Data Driven for startups - keboola
 
The Bumpy Road to Actionable SLOs
The Bumpy Road to Actionable SLOsThe Bumpy Road to Actionable SLOs
The Bumpy Road to Actionable SLOs
 
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...
Modern Product Data Workflows: How and Why: Embedded Analytics Interfaces For...
 
How and Why: Embedded Analytics Interfaces For Your SaaS Product
How and Why: Embedded Analytics Interfaces For Your SaaS ProductHow and Why: Embedded Analytics Interfaces For Your SaaS Product
How and Why: Embedded Analytics Interfaces For Your SaaS Product
 
Data_and_Analytics_Industry_IESE_v3.pdf
Data_and_Analytics_Industry_IESE_v3.pdfData_and_Analytics_Industry_IESE_v3.pdf
Data_and_Analytics_Industry_IESE_v3.pdf
 
How Gousto is moving to just-in-time personalization with Snowplow
How Gousto is moving to just-in-time personalization with SnowplowHow Gousto is moving to just-in-time personalization with Snowplow
How Gousto is moving to just-in-time personalization with Snowplow
 
SOP Planning and Optimization Solution-as-a-Service.pdf
SOP Planning and Optimization Solution-as-a-Service.pdfSOP Planning and Optimization Solution-as-a-Service.pdf
SOP Planning and Optimization Solution-as-a-Service.pdf
 
Superweek2019 dmo presentation
Superweek2019 dmo presentationSuperweek2019 dmo presentation
Superweek2019 dmo presentation
 
GeneOmalley_resume
GeneOmalley_resumeGeneOmalley_resume
GeneOmalley_resume
 
Better Living Through Analytics - Louis Cialdella Product School
Better Living Through Analytics - Louis Cialdella Product SchoolBetter Living Through Analytics - Louis Cialdella Product School
Better Living Through Analytics - Louis Cialdella Product School
 
Operationalizing Data Science: The Right Architecture and Tools
Operationalizing Data Science: The Right Architecture and ToolsOperationalizing Data Science: The Right Architecture and Tools
Operationalizing Data Science: The Right Architecture and Tools
 
Data Con LA 2019 - The challenges of data science for veteran media organizat...
Data Con LA 2019 - The challenges of data science for veteran media organizat...Data Con LA 2019 - The challenges of data science for veteran media organizat...
Data Con LA 2019 - The challenges of data science for veteran media organizat...
 
Gentile Consulting
Gentile ConsultingGentile Consulting
Gentile Consulting
 
Working with data.pdf
Working with data.pdfWorking with data.pdf
Working with data.pdf
 
Data Mining and Analytics
Data Mining and AnalyticsData Mining and Analytics
Data Mining and Analytics
 
Aligning Feature Delivery with OKRs by Gtmhub CPO
Aligning Feature Delivery with OKRs by Gtmhub CPOAligning Feature Delivery with OKRs by Gtmhub CPO
Aligning Feature Delivery with OKRs by Gtmhub CPO
 
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...
The C-Suite Data Advantage: How Workday Executives Reduce Costs and Make Bett...
 
Help Me, Help You: Supporting Your Data
Help Me, Help You: Supporting Your DataHelp Me, Help You: Supporting Your Data
Help Me, Help You: Supporting Your Data
 

More from Data For Good Regina

Working with survey data with Cameron Rayner
Working with survey data with Cameron RaynerWorking with survey data with Cameron Rayner
Working with survey data with Cameron RaynerData For Good Regina
 
Machine Learning Made Easy - Data for Good Regina
Machine Learning Made Easy - Data for Good ReginaMachine Learning Made Easy - Data for Good Regina
Machine Learning Made Easy - Data for Good ReginaData For Good Regina
 
Regina Food Summit - Data for Good
Regina Food Summit - Data for GoodRegina Food Summit - Data for Good
Regina Food Summit - Data for GoodData For Good Regina
 
Finding and using unique data sources
Finding and using unique data sourcesFinding and using unique data sources
Finding and using unique data sourcesData For Good Regina
 
Precision.ai Presentation @ Data for Good Regina - March
Precision.ai Presentation @ Data for Good Regina - MarchPrecision.ai Presentation @ Data for Good Regina - March
Precision.ai Presentation @ Data for Good Regina - MarchData For Good Regina
 
Data for Good - Data viz Challenge #2
Data for Good - Data viz Challenge #2Data for Good - Data viz Challenge #2
Data for Good - Data viz Challenge #2Data For Good Regina
 
SaskTel & Data for Good - Sean Milne
SaskTel & Data for Good - Sean MilneSaskTel & Data for Good - Sean Milne
SaskTel & Data for Good - Sean MilneData For Good Regina
 
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good Saskatchewan
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good SaskatchewanData Visualization Kick Off #1 - Nov 3 2020 - Data for Good Saskatchewan
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good SaskatchewanData For Good Regina
 
Data for Good - Strategic Overview October 2020
Data for Good - Strategic Overview October 2020Data for Good - Strategic Overview October 2020
Data for Good - Strategic Overview October 2020Data For Good Regina
 
A Playbook - Data Gathering To Storytelling
A Playbook - Data Gathering To StorytellingA Playbook - Data Gathering To Storytelling
A Playbook - Data Gathering To StorytellingData For Good Regina
 
Community Safety and Well Being Symposium 2020
Community Safety and Well Being Symposium 2020Community Safety and Well Being Symposium 2020
Community Safety and Well Being Symposium 2020Data For Good Regina
 
Data for Good: The Regina intersectoral Partnership
Data for Good: The Regina intersectoral PartnershipData for Good: The Regina intersectoral Partnership
Data for Good: The Regina intersectoral PartnershipData For Good Regina
 
Regina Early Years Family Centre - Data For Good
Regina Early Years Family Centre - Data For GoodRegina Early Years Family Centre - Data For Good
Regina Early Years Family Centre - Data For GoodData For Good Regina
 
ISM Environment Insights w/ Advanced Analytics - Data For Good
ISM Environment Insights w/ Advanced Analytics - Data For GoodISM Environment Insights w/ Advanced Analytics - Data For Good
ISM Environment Insights w/ Advanced Analytics - Data For GoodData For Good Regina
 
The United Way - Summer Success Program - Data For Good
The United Way - Summer Success Program - Data For GoodThe United Way - Summer Success Program - Data For Good
The United Way - Summer Success Program - Data For GoodData For Good Regina
 

More from Data For Good Regina (20)

april2023.pptx
april2023.pptxapril2023.pptx
april2023.pptx
 
march2023.pdf
march2023.pdfmarch2023.pdf
march2023.pdf
 
Working with survey data with Cameron Rayner
Working with survey data with Cameron RaynerWorking with survey data with Cameron Rayner
Working with survey data with Cameron Rayner
 
Machine Learning Made Easy - Data for Good Regina
Machine Learning Made Easy - Data for Good ReginaMachine Learning Made Easy - Data for Good Regina
Machine Learning Made Easy - Data for Good Regina
 
Regina Food Summit - Data for Good
Regina Food Summit - Data for GoodRegina Food Summit - Data for Good
Regina Food Summit - Data for Good
 
Finding and using unique data sources
Finding and using unique data sourcesFinding and using unique data sources
Finding and using unique data sources
 
Precision.ai Presentation @ Data for Good Regina - March
Precision.ai Presentation @ Data for Good Regina - MarchPrecision.ai Presentation @ Data for Good Regina - March
Precision.ai Presentation @ Data for Good Regina - March
 
Data for Good - Data viz Challenge #2
Data for Good - Data viz Challenge #2Data for Good - Data viz Challenge #2
Data for Good - Data viz Challenge #2
 
SaskTel & Data for Good - Sean Milne
SaskTel & Data for Good - Sean MilneSaskTel & Data for Good - Sean Milne
SaskTel & Data for Good - Sean Milne
 
Regina Food Bank & Data for Good
Regina Food Bank & Data for GoodRegina Food Bank & Data for Good
Regina Food Bank & Data for Good
 
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good Saskatchewan
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good SaskatchewanData Visualization Kick Off #1 - Nov 3 2020 - Data for Good Saskatchewan
Data Visualization Kick Off #1 - Nov 3 2020 - Data for Good Saskatchewan
 
Data for Good - Strategic Overview October 2020
Data for Good - Strategic Overview October 2020Data for Good - Strategic Overview October 2020
Data for Good - Strategic Overview October 2020
 
A Playbook - Data Gathering To Storytelling
A Playbook - Data Gathering To StorytellingA Playbook - Data Gathering To Storytelling
A Playbook - Data Gathering To Storytelling
 
Community Safety and Well Being Symposium 2020
Community Safety and Well Being Symposium 2020Community Safety and Well Being Symposium 2020
Community Safety and Well Being Symposium 2020
 
Data for Good: The Regina intersectoral Partnership
Data for Good: The Regina intersectoral PartnershipData for Good: The Regina intersectoral Partnership
Data for Good: The Regina intersectoral Partnership
 
Tourism Regina & Data
Tourism Regina & DataTourism Regina & Data
Tourism Regina & Data
 
U of R - Carbon Pricing Models
U of R - Carbon Pricing ModelsU of R - Carbon Pricing Models
U of R - Carbon Pricing Models
 
Regina Early Years Family Centre - Data For Good
Regina Early Years Family Centre - Data For GoodRegina Early Years Family Centre - Data For Good
Regina Early Years Family Centre - Data For Good
 
ISM Environment Insights w/ Advanced Analytics - Data For Good
ISM Environment Insights w/ Advanced Analytics - Data For GoodISM Environment Insights w/ Advanced Analytics - Data For Good
ISM Environment Insights w/ Advanced Analytics - Data For Good
 
The United Way - Summer Success Program - Data For Good
The United Way - Summer Success Program - Data For GoodThe United Way - Summer Success Program - Data For Good
The United Way - Summer Success Program - Data For Good
 

Recently uploaded

Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAbdelrhman abooda
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxStephen266013
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 

Recently uploaded (20)

Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
B2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docxB2 Creative Industry Response Evaluation.docx
B2 Creative Industry Response Evaluation.docx
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 

Data for Good Regina - 7shifts Presentation

  • 1. AI at 7shifts How we use data to increase the value of our restaurant scheduling system Logan Kopas Pronouns: He/Him
  • 3. Logan Kopas Data Team Lead A little about me I started out working as a full stack developer at NC Smart Call. I went back to school to do my masters in bioinformatics and deep learning. During my masters I began working at 7shifts and I’m loving it. I get to combine everything I’ve learned from undergrad, working at NC Smart Call, and my masters, as well as learn new skills and face new challenges. Additionally, I started a data science consulting company with Conor Lazarou to help other companies get started with data and analytics.
  • 4. Undergrad NC Smart Call Grad School 7shifts Introduction Who I am
  • 6. 7shifts ● ~160 employees ● Offices in Saskatoon, Toronto, and New York ● VC Funded ● Rapidly growing (except for covid)
  • 7. What we do ● Employee management for restaurants ○ Scheduling ○ Labour and POS integrations ○ Time tracking ○ Plus more
  • 9. Est. July 2019 Data Science Data Analysis Data Scientist ML expert Data Warehouse Developer Data storage and distribution Data Analyst Most data science-y analyst Data Analyst Tableau expert Data Team Lead No special skills Conor Tolo Will Kiara Data Developer Data Pipelines Jessie
  • 10. Data
  • 11. First things first, build a data warehouse
  • 12. Technology - Apache beam (python) - Postgres - Ansible - That’s it. Building a data warehouse Hosting - Compute Engine VM - Persistent Disk Storage
  • 13. Building a data warehouse Infrastructure
  • 14. Building a data warehouse Pipelines Storing data is only partially useful. - We need to get the data to our 3rd party tools so that our teammates can use it
  • 15. Building a data warehouse Pipelines Problem - Intercom wants info on “users” and “companies” - Salesforce wants info on “leads”, “opportunities”, “accounts”, and “contacts”
  • 16. Building a data warehouse Pipelines Solution - Push all events into Roughneck - Perform nightly update through Roughneck as well Event A ● User ID ● Company ID ● Event name Enrich from DB ● Lead ID ● Intercom ID ● Account Owner ● Etc. ● Salesforce Intercom Convert ● Proper fields and formatting for each destination
  • 17. Events are a large part of our incoming data. - Currently we dump it all into a data swamp - We also pipe the clean stuff into Amplitude - We have plans for an event warehouse Building a data warehouse Events
  • 18. Event Warehouse Hopes and Dreams - Graph database - Great for questions like - How many steps do users take from starting to build a schedule to publishing it? - What are the most common paths that arrive on the billing page? Building a data warehouse Events https://snowplowanalytics.com/blog/2018/03/26/building-a-model-for-atomic-event-data-as-a-graph/ session_start view_home_p age publish_ schedule User X User Y User A for next next notify notify
  • 20. PoP Model - Probability of Paying - Tracks company stats as they go through trial - Score from 0-1 - Allows sales to focus on customers that need an extra nudge - Indicator of Marketing lead quality AI for internal use PoP Model
  • 21. PoP Model - v1 - Random Forest - Based on different events and properties - Integrated POS system - Input employees birthdays - Published schedule - Employee logins AI for internal use PoP Model
  • 22. PoP Model - v2 - XGBoost - Incorporates events at different times in the trial - Number of employee logins in week 1 - Days to first published schedule AI for internal use PoP Model
  • 23. Section heading Page heading Other internal AI tools ● Plan suggestion model* ● Upsell suggestion model* ● Customer churn prediction model* *All under development Photo by NeONBRAND on Unsplash
  • 24. "Man, this shit makes my job so easy" Sales person
  • 25. "I was calling laundromats and nail salons, PoP saves my life, I actually call restaurants now" Sales person Photo by Rachel Park on Unsplash
  • 26. AI as a product
  • 27. Employee Engagement Score ● Tracks employee engagement ● Can be an early indicator of churn or other issues AI as a product Intro Autoscheduler ● Generates a schedule automatically ○ Based on predicted sales, optimal labour, previous employee schedules, events, etc.
  • 28. AI as a product Autoscheduler Autoscheduler recipe ● Dash of Sales Forecasting ● 1 part LabourNet ● 1 part ShiftMaker ● 1 part ShiftFiller ● Rinse glass with dash of sales forecasting ● Blend LabourNet and ShiftMaker together, strain into glass ● Sprinkle ShiftFiller on top ● Garnish and serve Photo by Mgg Vitchakorn on Unsplash
  • 30. Autoscheduler Sales Forecasting Sales Forecasting Ensemble ● Ensemble model combining 3 different sales forecasting algorithms ○ Short, medium, and long term forecasting models
  • 32. Autoscheduler LabourNet Deep Learning ● Tensorflow/Keras neural network with 1D-convolutional architecture ● Outputs optimal number of workers for each role throughout the day
  • 34. Autoscheduler ShiftMaker Shift ● Creates shifts to meet the labour demand curve ● Adheres to restaurant rules such as: min/max shift length, start/end time, etc. ● Also splits, combines, expands, trims, and adjusts shifts to meet requirements
  • 36. Autoscheduler ShiftFiller ShiftFiller ● Traditional AI that assigns employees to shifts ○ Heuristically solves the “nurse scheduling problem” ● Adheres to hard rules ○ Only 1 employee per shift, only roles the employee is assigned to, weekly OT thresholds ● Maximizes score based on soft rules ○ Common working times/days, target hours ● Stochastic hill climbing
  • 37. Questions? 7shifts.com/careers / flatland.AI logan.kopas@7shifts.com / logan@flatland.ai LinkedIn: Logan Kopas Twitter: @logankopas