SlideShare une entreprise Scribd logo
1  sur  19
Télécharger pour lire hors ligne
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
05/27/2021
Weekday Demand
Sensing at Walmart
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Walmart Stores
Overview
• The largest grocer in the U.S.
• Walmart employs over 2.3
million associates worldwide
• Over $500B annual sales
(over $330B in the U.S.)
• Over 11,300 stores worldwide
(over 4300 stores in the U.S.)
• Over 90% of the population
in the U.S. lives within 10
miles of a Walmart store
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Smart Forecasting
• A scalable forecasting platform to improve Walmart’s ability to predict customer demand
while improving item in-stocks and reducing food waste
• Adopted by all key departments in several global markets
• Generating weekly forecast for more than 100+ million item-store combinations every
week for the next 52 weeks
• Purpose:
• Inventory control (0-6 week horizon forecast)
• Purchase/vendor order and production planning
Our mission is to drive operational efficiency through
improvements in the ability to predict
customer demand
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Table of
contents Introduction
& Motivation
Model Results
Implementation
& scale
Introduction & Motivation
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Motivation
• Our store forecasting models are trained at scale every week, and weekly forecasts are
delivered every Monday
• We do not incorporate the most recent weekend sales in training our models as our ETL
processes start soon after Friday data has come in
• The idea for In Week Adjustments (IWA) project came from a Walmart Demand Manager
who devised and implemented a working prototype to prove out the concept
• The Weekend Sales Correction process uses replenishment rules to make practical store
forecast adjustments by accounting for factors such as days of supply and case pack sizes.
• IWA algorithm leverages historical sales patterns and linear models to predict the demand
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
In-week Adjustments (IWA) Algorithm
• A simple linear modeling approach to introduce forecast enhancements based on weekend
sales
• Adjusts initial weekly demand horizon 0 forecasts for Tuesday to Friday based on Saturday
and Sunday sales. E.g. if a product sells higher than forecasted on the weekend, we could
expect the remaining week’s sales to be higher than forecasted
• This algorithmic approach has been readily adopted by our business partners and has
consistently delivered business impact over the past year
• In addition to boosting the quality of the demand forecasts the algorithm reduces forecast
adjustment touches for busy demand managers without adding additional ETL overhead
Model
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Algorithm: Training
Load Input
Data
Pre-process
data
Train Linear
Model
• Load historical weekly
demand forecasts for
target categories
• Load 52 weeks of
store-item-week sales
• Calculate each item’s
daily sales %age using
robust estimators
• Remove all store-item-
week combinations
which may not need
adjustments
• For each item, select
the store-item-week
where it is overselling
or underselling
• Train a linear model to predict
demand as:
𝒅𝒆𝒎𝒂𝒏𝒅 ~ 𝒒𝒕𝒚𝒔𝒂𝒕 + 𝒒𝒕𝒚𝒔𝒖𝒏 + 𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Algorithm: Scoring
Pull current week sales data including Saturday, Sunday sales, on
hand qty, Saturday stock, received qty and promotions
Score current week store-item combinations using the model
𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕 𝒂𝒅𝒋𝒖𝒔𝒕𝒎𝒆𝒏𝒕 = 𝒔𝒄𝒐𝒓𝒆𝒅 𝒑𝒓𝒆𝒅𝒊𝒄𝒕𝒊𝒐𝒏 − 𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕
Accept the scored prediction as the new forecast if the
adjustment suggests adjusting store inventory based on the
current on hand quantity and case pack sizes of the item
Results
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Evaluation & Impact
• We performed a comprehensive back-test across all categories in produce and grocery for
a period of 12 weeks
• As shown in the plot below, IWA showed tremendous promise as evidenced by BPS
improvement in over 70% of produce categories
Walmart	produce	categories
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Impact Contd.
For the produce department, the algorithm has consistently delivered week on week 40+
basis points improvement in the forecast accuracy metric.
Implementation & scale
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Model Implementation
Current Scope – Runs for one department : Produce
• Input data stored in HDFS, Teradata and NFS drive
• Model runs on a single server, parallelized across 56 cores
Why Spark?
Enable scale up to new departments and markets through:
1. Cloud data storage: The current data storage is split across HDFS & Teradata which is
difficult to maintain and refresh. Redundant file transfer between storage systems
Spark ecosystem offers blob storage + Hive (delta tables) as a unified data storage
solution for easy maintainability
2. Runtime improvement: Partitioning the data by item will help large forecast and sales
files to be processed faster. Parquet I/O is lot faster than CSV
By saving runtime we will be able to train and score for more departments and
markets without risking high compute costs
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Planned Implementation
Data Storage
Data stored in
blob storage as
parquet
files partitioned
by item
Model training &
scoring
Parallelized
implementation
of the model on
Spark using
Spark DFs
Model outputs
Model outputs
saved to parquet
Model integrated
with the Smart
forecasting
platform
©2021 Walmart Inc. All Rights Reserved.
SENSITIVE INFORMATION CLASSIFICATION
Conclusion
Since its implementation in
March 2019, the IWA algorithm
has successfully delivered
hundreds of basis points
improvements week on week,
and helped reduce food waste
and improve customer availability
Thank you!();
Divya Hindupur
Jay Kakkar
Johann Posch
John Bowman
Feedback
Your feedback is important to us.
Don’t forget to rate and review the
sessions.

Contenu connexe

Tendances

04 movement types and transfer requirement
04 movement types and transfer requirement04 movement types and transfer requirement
04 movement types and transfer requirement
Asha Panda
 
Retailmerchandisebudgetplannng
RetailmerchandisebudgetplannngRetailmerchandisebudgetplannng
Retailmerchandisebudgetplannng
baabul
 
Merchandise planning
Merchandise planningMerchandise planning
Merchandise planning
Tarun Pandey
 

Tendances (20)

Intro to obppc architecture shelf savvy tool books
Intro to obppc architecture   shelf savvy tool booksIntro to obppc architecture   shelf savvy tool books
Intro to obppc architecture shelf savvy tool books
 
04 movement types and transfer requirement
04 movement types and transfer requirement04 movement types and transfer requirement
04 movement types and transfer requirement
 
Retailmerchandisebudgetplannng
RetailmerchandisebudgetplannngRetailmerchandisebudgetplannng
Retailmerchandisebudgetplannng
 
Presentation1 material master data
Presentation1 material master dataPresentation1 material master data
Presentation1 material master data
 
Marketing Growth Strategy Ppt Model
Marketing Growth Strategy Ppt ModelMarketing Growth Strategy Ppt Model
Marketing Growth Strategy Ppt Model
 
Merchandise planning
Merchandise planningMerchandise planning
Merchandise planning
 
52 Questions Your Customers Ask Before Buying
52 Questions Your Customers Ask Before Buying52 Questions Your Customers Ask Before Buying
52 Questions Your Customers Ask Before Buying
 
Data Warehouse Concepts and Architecture
Data Warehouse Concepts and ArchitectureData Warehouse Concepts and Architecture
Data Warehouse Concepts and Architecture
 
Case analysis walmart case group i
Case analysis walmart case group iCase analysis walmart case group i
Case analysis walmart case group i
 
SAP Material master general document
SAP Material master   general documentSAP Material master   general document
SAP Material master general document
 
Retail Data Warehouse
Retail Data WarehouseRetail Data Warehouse
Retail Data Warehouse
 
7 eleven full hd
7 eleven full hd7 eleven full hd
7 eleven full hd
 
Supply Chain Strategy at 7-Eleven
Supply Chain Strategy at 7-ElevenSupply Chain Strategy at 7-Eleven
Supply Chain Strategy at 7-Eleven
 
2020-T1 Business Intelligence
2020-T1 Business Intelligence2020-T1 Business Intelligence
2020-T1 Business Intelligence
 
Basics of demand management for idiots
Basics of demand management for idiotsBasics of demand management for idiots
Basics of demand management for idiots
 
Data Science @ Instacart
Data Science @ InstacartData Science @ Instacart
Data Science @ Instacart
 
BI Presentation
BI PresentationBI Presentation
BI Presentation
 
Sap sd overview training
Sap sd overview trainingSap sd overview training
Sap sd overview training
 
SAP Flexible Planning
SAP Flexible PlanningSAP Flexible Planning
SAP Flexible Planning
 
A Merchant's Guide to Retail Math 101
A Merchant's Guide to Retail Math 101A Merchant's Guide to Retail Math 101
A Merchant's Guide to Retail Math 101
 

Similaire à Weekday Demand Sensing at Walmart

130219 CPC Introduction AE
130219 CPC Introduction AE130219 CPC Introduction AE
130219 CPC Introduction AE
Rohit Dandona
 
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
elliotkimberlee
 
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
HostedbyConfluent
 
CM Webinar B2C EMI Preview
CM Webinar B2C EMI PreviewCM Webinar B2C EMI Preview
CM Webinar B2C EMI Preview
Mirakl
 
Inventory Optimization for Multi-Location Distribution
Inventory Optimization for Multi-Location DistributionInventory Optimization for Multi-Location Distribution
Inventory Optimization for Multi-Location Distribution
Jim Kolassa
 
439 Michael Zazzera Hyperion Final - Soulutions 2001
439 Michael Zazzera Hyperion Final - Soulutions 2001439 Michael Zazzera Hyperion Final - Soulutions 2001
439 Michael Zazzera Hyperion Final - Soulutions 2001
Michael Zazzera
 
SALES_FORECASTING of sparkflows.pdf
SALES_FORECASTING of sparkflows.pdfSALES_FORECASTING of sparkflows.pdf
SALES_FORECASTING of sparkflows.pdf
Sparkflows
 
Ucg ems-distribution-november2013
Ucg ems-distribution-november2013Ucg ems-distribution-november2013
Ucg ems-distribution-november2013
Noah Truax
 

Similaire à Weekday Demand Sensing at Walmart (20)

130219 CPC Introduction AE
130219 CPC Introduction AE130219 CPC Introduction AE
130219 CPC Introduction AE
 
HICAM Presentation Oracle Symposium.pdf
HICAM Presentation Oracle Symposium.pdfHICAM Presentation Oracle Symposium.pdf
HICAM Presentation Oracle Symposium.pdf
 
Swift-sense Slides
Swift-sense Slides Swift-sense Slides
Swift-sense Slides
 
Joachim_Sculte_Hungary_Appsday_Demantra_081007.ppt
Joachim_Sculte_Hungary_Appsday_Demantra_081007.pptJoachim_Sculte_Hungary_Appsday_Demantra_081007.ppt
Joachim_Sculte_Hungary_Appsday_Demantra_081007.ppt
 
Data warehousing - Dr. Radhika Kotecha
Data warehousing - Dr. Radhika KotechaData warehousing - Dr. Radhika Kotecha
Data warehousing - Dr. Radhika Kotecha
 
KRANTHI_ABAP_RESUME
KRANTHI_ABAP_RESUMEKRANTHI_ABAP_RESUME
KRANTHI_ABAP_RESUME
 
Analytic servise BI Datawiz
Analytic servise BI DatawizAnalytic servise BI Datawiz
Analytic servise BI Datawiz
 
Leading a Supply Chain Turnaround - Whirlpool
Leading a Supply Chain Turnaround - WhirlpoolLeading a Supply Chain Turnaround - Whirlpool
Leading a Supply Chain Turnaround - Whirlpool
 
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
1.1DetailsCase Study Scenario - Global Trading PLCGlo.docx
 
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
Speed without accidents : Kafka Exemplified | Dhawal Soni and Suman Pattnaik,...
 
BEFORE! Predictive Analytics
BEFORE! Predictive Analytics BEFORE! Predictive Analytics
BEFORE! Predictive Analytics
 
CM Webinar B2C EMI Preview
CM Webinar B2C EMI PreviewCM Webinar B2C EMI Preview
CM Webinar B2C EMI Preview
 
Magneto implementation by synoptek
Magneto implementation by synoptekMagneto implementation by synoptek
Magneto implementation by synoptek
 
Inventory Optimization for Multi-Location Distribution
Inventory Optimization for Multi-Location DistributionInventory Optimization for Multi-Location Distribution
Inventory Optimization for Multi-Location Distribution
 
439 Michael Zazzera Hyperion Final - Soulutions 2001
439 Michael Zazzera Hyperion Final - Soulutions 2001439 Michael Zazzera Hyperion Final - Soulutions 2001
439 Michael Zazzera Hyperion Final - Soulutions 2001
 
Data warehousev2.1
Data warehousev2.1Data warehousev2.1
Data warehousev2.1
 
SALES_FORECASTING of sparkflows.pdf
SALES_FORECASTING of sparkflows.pdfSALES_FORECASTING of sparkflows.pdf
SALES_FORECASTING of sparkflows.pdf
 
Webinar_DemandPlanning_Forecasting.pdf
Webinar_DemandPlanning_Forecasting.pdfWebinar_DemandPlanning_Forecasting.pdf
Webinar_DemandPlanning_Forecasting.pdf
 
Land O' Lakes: Harnessing Big Data Variety
Land O' Lakes: Harnessing Big Data VarietyLand O' Lakes: Harnessing Big Data Variety
Land O' Lakes: Harnessing Big Data Variety
 
Ucg ems-distribution-november2013
Ucg ems-distribution-november2013Ucg ems-distribution-november2013
Ucg ems-distribution-november2013
 

Plus de Databricks

Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized Platform
Databricks
 
Stage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationStage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI Integration
Databricks
 
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchSimplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Databricks
 
Raven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesRaven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction Queries
Databricks
 
Processing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkProcessing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache Spark
Databricks
 

Plus de Databricks (20)

DW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptx
 
Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1
 
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2
 
Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2Data Lakehouse Symposium | Day 2
Data Lakehouse Symposium | Day 2
 
Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4
 
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
 
Democratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized Platform
 
Learn to Use Databricks for Data Science
Learn to Use Databricks for Data ScienceLearn to Use Databricks for Data Science
Learn to Use Databricks for Data Science
 
Why APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML MonitoringWhy APM Is Not the Same As ML Monitoring
Why APM Is Not the Same As ML Monitoring
 
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixThe Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
 
Stage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI IntegrationStage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI Integration
 
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorchSimplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorch
 
Scaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on KubernetesScaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on Kubernetes
 
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark PipelinesScaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
 
Sawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature AggregationsSawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature Aggregations
 
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkRedis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
 
Re-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkRe-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and Spark
 
Raven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction QueriesRaven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction Queries
 
Processing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache SparkProcessing Large Datasets for ADAS Applications using Apache Spark
Processing Large Datasets for ADAS Applications using Apache Spark
 
Massive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta LakeMassive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta Lake
 

Dernier

Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
gajnagarg
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
HyderabadDolls
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
gajnagarg
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
Health
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
ahmedjiabur940
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
wsppdmt
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
nirzagarg
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
gajnagarg
 

Dernier (20)

Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
 
Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbers
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
 
Top Call Girls in Balaghat 9332606886Call Girls Advance Cash On Delivery Ser...
Top Call Girls in Balaghat  9332606886Call Girls Advance Cash On Delivery Ser...Top Call Girls in Balaghat  9332606886Call Girls Advance Cash On Delivery Ser...
Top Call Girls in Balaghat 9332606886Call Girls Advance Cash On Delivery Ser...
 
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
Sonagachi * best call girls in Kolkata | ₹,9500 Pay Cash 8005736733 Free Home...
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
 
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
 
Gomti Nagar & best call girls in Lucknow | 9548273370 Independent Escorts & D...
Gomti Nagar & best call girls in Lucknow | 9548273370 Independent Escorts & D...Gomti Nagar & best call girls in Lucknow | 9548273370 Independent Escorts & D...
Gomti Nagar & best call girls in Lucknow | 9548273370 Independent Escorts & D...
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
 

Weekday Demand Sensing at Walmart

  • 1. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION 05/27/2021 Weekday Demand Sensing at Walmart
  • 2. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Walmart Stores Overview • The largest grocer in the U.S. • Walmart employs over 2.3 million associates worldwide • Over $500B annual sales (over $330B in the U.S.) • Over 11,300 stores worldwide (over 4300 stores in the U.S.) • Over 90% of the population in the U.S. lives within 10 miles of a Walmart store
  • 3. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Smart Forecasting • A scalable forecasting platform to improve Walmart’s ability to predict customer demand while improving item in-stocks and reducing food waste • Adopted by all key departments in several global markets • Generating weekly forecast for more than 100+ million item-store combinations every week for the next 52 weeks • Purpose: • Inventory control (0-6 week horizon forecast) • Purchase/vendor order and production planning Our mission is to drive operational efficiency through improvements in the ability to predict customer demand
  • 4. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Table of contents Introduction & Motivation Model Results Implementation & scale
  • 6. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Motivation • Our store forecasting models are trained at scale every week, and weekly forecasts are delivered every Monday • We do not incorporate the most recent weekend sales in training our models as our ETL processes start soon after Friday data has come in • The idea for In Week Adjustments (IWA) project came from a Walmart Demand Manager who devised and implemented a working prototype to prove out the concept • The Weekend Sales Correction process uses replenishment rules to make practical store forecast adjustments by accounting for factors such as days of supply and case pack sizes. • IWA algorithm leverages historical sales patterns and linear models to predict the demand
  • 7. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION In-week Adjustments (IWA) Algorithm • A simple linear modeling approach to introduce forecast enhancements based on weekend sales • Adjusts initial weekly demand horizon 0 forecasts for Tuesday to Friday based on Saturday and Sunday sales. E.g. if a product sells higher than forecasted on the weekend, we could expect the remaining week’s sales to be higher than forecasted • This algorithmic approach has been readily adopted by our business partners and has consistently delivered business impact over the past year • In addition to boosting the quality of the demand forecasts the algorithm reduces forecast adjustment touches for busy demand managers without adding additional ETL overhead
  • 9. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Algorithm: Training Load Input Data Pre-process data Train Linear Model • Load historical weekly demand forecasts for target categories • Load 52 weeks of store-item-week sales • Calculate each item’s daily sales %age using robust estimators • Remove all store-item- week combinations which may not need adjustments • For each item, select the store-item-week where it is overselling or underselling • Train a linear model to predict demand as: 𝒅𝒆𝒎𝒂𝒏𝒅 ~ 𝒒𝒕𝒚𝒔𝒂𝒕 + 𝒒𝒕𝒚𝒔𝒖𝒏 + 𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕
  • 10. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Algorithm: Scoring Pull current week sales data including Saturday, Sunday sales, on hand qty, Saturday stock, received qty and promotions Score current week store-item combinations using the model 𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕 𝒂𝒅𝒋𝒖𝒔𝒕𝒎𝒆𝒏𝒕 = 𝒔𝒄𝒐𝒓𝒆𝒅 𝒑𝒓𝒆𝒅𝒊𝒄𝒕𝒊𝒐𝒏 − 𝒇𝒐𝒓𝒆𝒄𝒂𝒔𝒕 Accept the scored prediction as the new forecast if the adjustment suggests adjusting store inventory based on the current on hand quantity and case pack sizes of the item
  • 12. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Evaluation & Impact • We performed a comprehensive back-test across all categories in produce and grocery for a period of 12 weeks • As shown in the plot below, IWA showed tremendous promise as evidenced by BPS improvement in over 70% of produce categories Walmart produce categories
  • 13. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Impact Contd. For the produce department, the algorithm has consistently delivered week on week 40+ basis points improvement in the forecast accuracy metric.
  • 15. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Model Implementation Current Scope – Runs for one department : Produce • Input data stored in HDFS, Teradata and NFS drive • Model runs on a single server, parallelized across 56 cores Why Spark? Enable scale up to new departments and markets through: 1. Cloud data storage: The current data storage is split across HDFS & Teradata which is difficult to maintain and refresh. Redundant file transfer between storage systems Spark ecosystem offers blob storage + Hive (delta tables) as a unified data storage solution for easy maintainability 2. Runtime improvement: Partitioning the data by item will help large forecast and sales files to be processed faster. Parquet I/O is lot faster than CSV By saving runtime we will be able to train and score for more departments and markets without risking high compute costs
  • 16. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Planned Implementation Data Storage Data stored in blob storage as parquet files partitioned by item Model training & scoring Parallelized implementation of the model on Spark using Spark DFs Model outputs Model outputs saved to parquet Model integrated with the Smart forecasting platform
  • 17. ©2021 Walmart Inc. All Rights Reserved. SENSITIVE INFORMATION CLASSIFICATION Conclusion Since its implementation in March 2019, the IWA algorithm has successfully delivered hundreds of basis points improvements week on week, and helped reduce food waste and improve customer availability
  • 18. Thank you!(); Divya Hindupur Jay Kakkar Johann Posch John Bowman
  • 19. Feedback Your feedback is important to us. Don’t forget to rate and review the sessions.