Stas Sushkov is a market planning and store chain development expert with Pizza Hut International. He led analysis and strategic development for over 10,000 Pizza Hut restaurants globally. Some of his responsibilities included developing market planning standards and methodologies, implementing a store lifecycle management software, and developing penetration strategies for new Pizza Hut concepts. He has extensive experience conducting market planning for Pizza Hut in various countries around the world.
Geo@Work, keynote from Carto Spatial Data Science conferenceCarl Anderson
Keynote given at Carto Spatial Data Science conference (https://carto.com/spatial-data-conference/), December 1, 2017.
How and why is location intelligence important at WeWork? A global provider of flexible work space, WeWork is growing at an incredible pace. With 178 locations in 53 cities and 18 countries, and doubling each year, and taking on decade+ leases, it is crucial that we take site selection seriously. In this talk, we’ll cover our initial efforts to bring geospatial thinking, tooling, and predictive models to the organization. We’ll cover some use cases, models, as well as some of the challenges of tackling geocentric data science at global scale.
What is geodemography and how can it be used in improving student recruitment? How can geodemography be used to improve predictive models? This session will introduce you to Descriptor PLUS, a service providing educationally-relevant geodemographic information
to admission and enrollment managers interested in knowing more about college selection, choice, and persistence. Descriptor PLUS was revised and expanded in 2011 and this session will review these important changes.
East Massachusetts Geodemographic ClassificationStas Sushkov
The presentation outlines the process of East Massachusetts Geodemographic Classification design following methodology developed by Dr.Dan Vickers (University of Sheffield).
Geo@Work, keynote from Carto Spatial Data Science conferenceCarl Anderson
Keynote given at Carto Spatial Data Science conference (https://carto.com/spatial-data-conference/), December 1, 2017.
How and why is location intelligence important at WeWork? A global provider of flexible work space, WeWork is growing at an incredible pace. With 178 locations in 53 cities and 18 countries, and doubling each year, and taking on decade+ leases, it is crucial that we take site selection seriously. In this talk, we’ll cover our initial efforts to bring geospatial thinking, tooling, and predictive models to the organization. We’ll cover some use cases, models, as well as some of the challenges of tackling geocentric data science at global scale.
What is geodemography and how can it be used in improving student recruitment? How can geodemography be used to improve predictive models? This session will introduce you to Descriptor PLUS, a service providing educationally-relevant geodemographic information
to admission and enrollment managers interested in knowing more about college selection, choice, and persistence. Descriptor PLUS was revised and expanded in 2011 and this session will review these important changes.
East Massachusetts Geodemographic ClassificationStas Sushkov
The presentation outlines the process of East Massachusetts Geodemographic Classification design following methodology developed by Dr.Dan Vickers (University of Sheffield).
A sample of possibilities to use geomarketing tools for empowering business solutions.
Geomarketing solves problems in companies and makes always right decisions.
Positioning for Retail Recovery: The Role of Predictive Analytics Fueled by M...Precisely
As parts of the world show signs of emergence from the initial Covid-19 onslaught, retailers are opening their doors and looking to reduce risk and increase opportunities through strategies which are backed by highly accurate data and analytics. Retailers who understand context and can make location intelligent marketing plays will win, with mobile trace data playing a key role in taking contextual consumer understanding to the next level.
In this webinar, discover how using mobile trace data helps the most effective retailers and restaurants to understand previous pedestrian footfall and predict the most likely areas where retail activity will return. This understanding is helping to drive highly targeted multi-channel marketing programs for leaders in the industry.
This on-demand webinar will also cover:
- The principles of mobile trace data and what makes it a game-changing data set for the retail community
- How to use mobile trace data analytics to drive retail strategies around site selection and marketing in a transformative environment
- Showcasing of retailer use cases where predictive analytics fueled by mobile trace data is being used to compete and win in the market
Best Practices in Economic Development Websites for Better Results Atlas Integrated
Ben Wright, Atlas CEO & Guillermo Mazier, Atlas’ Director of Strategic Accounts, will cover the latest theory, website examples from around the country and 2014's best practices of the biggest game changer economic development marketing has ever seen. Takeaway real tools and techniques to review and revamp your most important marketing asset – your website.
Best Practices in Economic Development Websites Better ResultsAtlas Advertising
en Wright, Atlas CEO & Guillermo Mazier, Atlas’ Director of Strategic Accounts, will cover the latest theory, website examples from around the country and 2014's best practices of the biggest game changer economic development marketing has ever seen. Takeaway real tools and techniques to review and revamp your most important marketing asset – your website
How to use publicly available and private web metrics for UX strategy, research, benchmarking, concepting and testing. This talk was given in NYC at UX Acrobatics, March 2014; a revised version at UX + Data Meetup NY, June 2014; revised for UXPA International, July 2014; and updated again for General Assembly San Francisco 1-day workshop, August 3, 2014.
06. DIGGIT MARIUS IVANOVAS (Httpool Baltics): Personalizirane marketinške akt...mateja repovž
Kompleksnost medijskega sveta zaznavamo, kot velike količine razpršenih in nepreglednih podatkov brez skupnega imenovalca. Integracija različnih virov podatkov, zbranih na enema mestu in prilagoditev vsem akterjem v marketingu in prodaji prispeva k hitrejšim in bolj utemeljenim odločitvam.
A sample of possibilities to use geomarketing tools for empowering business solutions.
Geomarketing solves problems in companies and makes always right decisions.
Positioning for Retail Recovery: The Role of Predictive Analytics Fueled by M...Precisely
As parts of the world show signs of emergence from the initial Covid-19 onslaught, retailers are opening their doors and looking to reduce risk and increase opportunities through strategies which are backed by highly accurate data and analytics. Retailers who understand context and can make location intelligent marketing plays will win, with mobile trace data playing a key role in taking contextual consumer understanding to the next level.
In this webinar, discover how using mobile trace data helps the most effective retailers and restaurants to understand previous pedestrian footfall and predict the most likely areas where retail activity will return. This understanding is helping to drive highly targeted multi-channel marketing programs for leaders in the industry.
This on-demand webinar will also cover:
- The principles of mobile trace data and what makes it a game-changing data set for the retail community
- How to use mobile trace data analytics to drive retail strategies around site selection and marketing in a transformative environment
- Showcasing of retailer use cases where predictive analytics fueled by mobile trace data is being used to compete and win in the market
Best Practices in Economic Development Websites for Better Results Atlas Integrated
Ben Wright, Atlas CEO & Guillermo Mazier, Atlas’ Director of Strategic Accounts, will cover the latest theory, website examples from around the country and 2014's best practices of the biggest game changer economic development marketing has ever seen. Takeaway real tools and techniques to review and revamp your most important marketing asset – your website.
Best Practices in Economic Development Websites Better ResultsAtlas Advertising
en Wright, Atlas CEO & Guillermo Mazier, Atlas’ Director of Strategic Accounts, will cover the latest theory, website examples from around the country and 2014's best practices of the biggest game changer economic development marketing has ever seen. Takeaway real tools and techniques to review and revamp your most important marketing asset – your website
How to use publicly available and private web metrics for UX strategy, research, benchmarking, concepting and testing. This talk was given in NYC at UX Acrobatics, March 2014; a revised version at UX + Data Meetup NY, June 2014; revised for UXPA International, July 2014; and updated again for General Assembly San Francisco 1-day workshop, August 3, 2014.
06. DIGGIT MARIUS IVANOVAS (Httpool Baltics): Personalizirane marketinške akt...mateja repovž
Kompleksnost medijskega sveta zaznavamo, kot velike količine razpršenih in nepreglednih podatkov brez skupnega imenovalca. Integracija različnih virov podatkov, zbranih na enema mestu in prilagoditev vsem akterjem v marketingu in prodaji prispeva k hitrejšim in bolj utemeljenim odločitvam.
The Building Blocks of QuestDB, a Time Series Databasejavier ramirez
Talk Delivered at Valencia Codes Meetup 2024-06.
Traditionally, databases have treated timestamps just as another data type. However, when performing real-time analytics, timestamps should be first class citizens and we need rich time semantics to get the most out of our data. We also need to deal with ever growing datasets while keeping performant, which is as fun as it sounds.
It is no wonder time-series databases are now more popular than ever before. Join me in this session to learn about the internal architecture and building blocks of QuestDB, an open source time-series database designed for speed. We will also review a history of some of the changes we have gone over the past two years to deal with late and unordered data, non-blocking writes, read-replicas, or faster batch ingestion.
Analysis insight about a Flyball dog competition team's performanceroli9797
Insight of my analysis about a Flyball dog competition team's last year performance. Find more: https://github.com/rolandnagy-ds/flyball_race_analysis/tree/main
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
2. Global Market Planner
Yum! Brands. Pizza Hut Int.
(2014 - Present)
Led the analysis and strategic development for Pizza Hut International
(10,000+ restaurants in 100+ countries).
Developed market planning global standards and methodologies
Implemented Store Lifecycle Management Software
Penetration strategy development for the New PH Concept
3. Guiding Pizza Hut With Precise Market
Planning
UK
TURKEY
RUSSIA
CANADA
GERMANY
BRAZIL
JAPAN
S. AFRICA
INDONESIA
MEXICO
FRANCE
INDIA
COMPLETEDPROGRESSOPPORTUNITY
ADVANCEDMARKETPLANS
UK
TURKEY
RUSSIA
CANADA
GERMANY
BRAZIL
JAPAN
S. AFRICA
INDONESIA
MEXICO
FRANCE
INDIA…
Mapping Top Markets
Map and analyze existing stores
Analyze city demographics
Analyze Competitor/ generators/ traffic
Field Research - City trip and Street View
Maps
Identify and map Hot Spots
Identify and map potential Trade Zones
Define Asset Portfolio
Build Stores and Repeat
Market planning Process
4. Market Planning
Trips Taken
To research
regional cities’
potential and
identify proposed
Hot Spots and
Trade Zones
Picture
BRAZIL Market Planning Case study
Top Cities
Selected and
PrioritizedDesktop research
for city potential
has been
performed
100+ existing PH stores. Country potential 1000+ stores.
The goal is develop a market planning methodology for Top-20 cities
Hot Spots Mapped
in SLMS
Identified potential
HS were analyzed
and then mapped
in GIS
Potential TZ
Mapped in SLMS
Potential TZ have
been created
based on 8-min
drive-time
catchments, AB
class pop and HH
data
Picture
São Paulo (Metro)
Salvador
Brasília
Fortaleza
Belo Horizonte
Manaus
Curitiba
Recife
Porto Alegre
5. Taiwan Case study
Existing TZ Digitized
Restaurant
delivery maps
were scanned and
digitized for
upload to GIS
Picture
Uncovered High
Exist. TZ Density
Hard to find areas
for new potential
TZs
Picture
200 existing PH stores. Country potential ~350 stores.
The goal is to identify potential TZ to convince FZ to open more stores.
Store and TZ Data
Analyzed
High TZ size 30k
hh instead of 20k
Low Delivery
Trans > 28%
Low correlation
between TZ size
(hh) and sales
Picture
Existing TZ Size
Reduction Suggested
To give space for
new TZs and
stores
Penetration to tier
3 cities was
suggested as well
Picture
6. DATA TOOLS KNOWLEDGE
FUEL ENGINE PEOPLE
SOFTWARE LAUNCH PROJECT:
Cloud GIS/Store Lifecycle Management
System
GIS
Analysis
Project
Managem
ent
Asset
Data
Base
7. SLMS/GiS Implementation
12 Business Units. 2 Brands. Budget $1.5M+…
• W Europe
• CE Europe
• Africa
• Russia
• Turkey
• SOPAC
• Asia
• Thailand
• UK
• Canada
• LA&C
• MENA
8. • Analyzed existing stores in
selected markets
• Developed site and TZ selection
criteria
• Designed New Concept Tiering
strategy
New Asset Type Concept Launch
9. Yum! Restaurants Russia
Market Planner
(2010-2014)
Witnessed and contributed to the tremendous success of Yum! Brands
in Russia.
Drove net unit growth by development of solid strategic plans.
Set-up and led the market planning and analytical process.
Created Market plans, analyzed sites, submitted new store CAPEXes,
Developed multiple analytical tools (sales forecasting, site scoring,
mall ranking and others)
Trained and hand-overed the process to the right successor.
10. 14 19
39
70
114
2010 2011 2012 2013 2014
Yum! Russia New Store Builds
Contributed to Significant Growth of New
Units in Russia
11. Established and Led Market Mapping
Process in Russia
• 40+ market plans of cities
Russia and CIS countries
• Developed the methodology
• Set-up TZ and site criteria
• Trained the team how to
apply and how to update
market plan
• 250+ stores were opened in
identified TZ
12. Cloud GIS
Market Planner
RE managers in the office RE managers in the field
Leadership Team
Set-up Cloud GIS for the Development Team
13. Compiled CAPEXes and submitted
to the Investment Committee
Trade Zone Location
Trade Zone
Population Density
Generators and Competition Sales Estimations
Market Plan w Trade Zone Priority
14. Designed and Executed Restaurant Guest
Surveys (RTZ Studies)
TZ Guest Origin Map
Guests Trip Origin and Trip Destination
Guests Trip Origin and Trip Destination
15. Developed Store Sales Estimation Models
Carry-Out Orders Map Delivery Orders Map
New Site Sales Estimations
Based on RTZ results and delivery addresses analysis identified density of carry-out and
delivery order. Developed formula that estimates store transactions and sales.
17. Designed and Launched Site/Store
Scorecarding Process
71
Site/store assessment tool
• Mobile iOS-based GPS-supported
scorecard
• iForm Platform
• Custom variables and LOVs
• Site/Store Scoring Formula
• Sales Estimation Formula
• Auto sync and data upload
18. Developed the City Scoring methodology of the Russian cites.
Ranked, prioritized and estimated potential of 2,500 towns and cities.
Provided In-depth Analytics
19. Store Seating Optimization Analysis
113 170 255
74 111 166
62 94 140
0
50
100
150
200
250
Mon
Mon
Mon
Mon
Tue
Tue
Tue
Tue
Wed
Wed
Wed
Wed
Thu
Thu
Thu
Thu
Fri
Fri
Fri
Fri
Sat
Sat
Sat
Sun
Sun
Sun
Moscow Flagship Store
Transactions Flow During the
Week
2000
1500
1250
20min 30min 45min
Carry out 10%
Occupancy
rate
1,7 seats per person
Daily Transactions
Seating time
Trans per day 1950
Seats 299
Store Data
Provided In-depth Analytics
20. GIS Support to Local Store Marketing
Online and Mobile LSM Maps for Store Managers
MAP LINK
LSM Manual for New GMs
21. Geodemographics
For research purposes designed and developed Geodemographic
Classification of US population based on Census 2000 data.
Provided GIS and geomarketing analysis (customer profiling,
customer segmentation, retail trade area evaluation, site selection,
marketing campaign planning) using the classification results
22. Demographic and
GIS data selection
Variables selection
Variables
standardization
Clustering
(K-means)
Identification of
cluster numbers
Interpretation,
testing and
mapping of
clusters
Methodology of
USA Geo-Demographic Segmentation
See for More Details
23. 7 US Population Groups
18 Sub-groups (Clusters)
Segmentation Outcomes
24. Identified Clusters Description
Cluster 5.1- Upscale Couples
“Upscale Couples” is a cluster of rich people with large
share of men and women between 45 and 65 who live in
suburban areas within the vicinity of large US cities.
Their incomes are two times higher than US average
Significant share of these
group members is self-
employed
Those who work prefer to use personal
vehicle to get to work, and majority of them
leave home between 8-10am.