"No one is harder on a talented person than the person themselves" - Linda Wilkinson ; "Trust your guts and don't follow the herd" ; "Validate direction not destination" ;
Showing posts with label Retail. Show all posts
Showing posts with label Retail. Show all posts

September 26, 2024

🚀 Celebrating a Year of GenAI Use Case Success in Retail! 🎉

It's been over a year since my Retail adoption #GenAI use case went live for a leading U.S. specialty retailer on August 17, 2023. 

The results? Double-digit improvement in user page conversions! 📈

🔍 Key Insights:

Innovation Over Integration: Initially, I didn't showcase #GenAI use cases to the #CTO. Instead, I presented a #ReimaginedWorkflow for:

  • Customers
  • Support analysts
  • Procurement teams
  • Digital Asset Management

Rethinking AI/ML Implementation: It's not about wrapping AI around existing processes. True impact comes from:

  • New engagement models
  • Innovative interactions
  • Blending creative solutions

Success Factors in Production:

  • Data Quality 🏆
  • Innovative use of GenAI
  • Tailored solutions (not patchwork fixes)
  • Rigorous testing in production environments

Beyond Demos: Real adoption comes from solving genuine user needs, not just showcasing capabilities.

  • 💡 Lesson Learned: To make #AI truly impactful, we must explore new ways of engagement, foster creativity, and innovate by combining diverse ideas.
  • 👥 Collaboration Opportunity: Are you working on similar AI strategies or use cases? Let's connect and collaborate! Share your experiences in the comments.

#AIStrategy #RetailInnovation #DataDrivenDecisions #DigitalTransformation #AIAdoption #TechLeadership #InnovationInRetail #AISuccessStory

Who else is seeing success with GenAI in their industry? Let's discuss! 👇


March 24, 2023

Ideas - create exceptional customer experiences - Retail

You need to have a truckload of ideas. This interesting report has a lot of insights on areas to focus on.

Ref - Link

Some key pointers

Touch point-based analysis


Customer feedback-based Insights


Competitor based comparison


Impact of each level of engagement



Ref - Link



Keep Exploring!!!




January 31, 2023

Customer360 - Personal - GPT

Building some fundamentals with GPT :)

What are different third party sources retailers use to discover customers

1. Social media platforms (Facebook, Twitter, Instagram, etc.)
2. Email marketing
3. Affiliate marketing
4. Online advertising (Google Ads, Bing Ads, etc.)
5. Influencer marketing
6. Online review sites (Yelp, TripAdvisor, etc.)
7. Mobile marketing
8. Search engine optimization (SEO)
9. Referral programs
10. Content marketing

What are different customer persona for retail fashion industry

1. The Trendsetter: This customer is always looking for the latest fashion trends and loves to be the first to wear them. They are willing to pay a premium for the latest styles and are always on the lookout for the newest fashion collections.
2. The Bargain Hunter: This customer loves to find the best deals and discounts on fashion items. They are always looking for the best prices and are willing to wait for sales or discounts to purchase items.
3. The Quality Seeker: This customer is willing to pay for quality fashion items that will last them for years. They are willing to invest in higher-end fashion items that are made with quality materials and craftsmanship.
4. The Comfort Seeker: This customer is looking for fashion items that are comfortable and stylish. They are willing to pay for items that are both fashionable and comfortable.
5. The Classic Dresser: This customer is looking for timeless fashion items that will never go out of style. They are looking for items that will last them for years and are willing to pay for quality and timeless fashion items.

What are different customer persona for food consumption dining industry

1. The Foodie: This customer is passionate about food and loves to try new dishes. They are always looking for the latest trends in food and are willing to pay for quality.
2. The Health Conscious: This customer is focused on eating healthy and nutritious meals. They are willing to pay for organic and natural ingredients and are always on the lookout for healthy options.
3. The Budget Conscious: This customer is looking for the best value for their money. They are always looking for discounts and deals and are willing to sacrifice quality for a lower price.
4. The Socialite: This customer loves to go out and socialize with friends. They are looking for a fun atmosphere and are willing to pay for a good time.
5. The Family: This customer is looking for a place to take the family. They are looking for a comfortable atmosphere and are willing to pay for convenience.

What are different customer persona for customer spending
1. The Budget-Conscious Shopper: This customer is focused on getting the best value for their money and is always looking for discounts and deals. They are likely to comparison shop and research products before making a purchase.
2. The Impulse Buyer: This customer is driven by emotion and tends to make purchases on a whim. They are likely to be drawn to flashy displays and attractive packaging.
3. The Loyal Customer: This customer is loyal to a particular brand and will always purchase from that brand regardless of cost or convenience. They are likely to be influenced by loyalty programs and customer service.
4. The Early Adopter: This customer is always looking for the newest products and trends. They are likely to be influenced by word-of-mouth and social media.
5. The Experiential Shopper: This customer is focused on the shopping experience and is likely to be influenced by store layout, customer service, and overall atmosphere.

What are different customer persona for healthcare spending
1. The Young Professional: This customer is a young adult who is just starting out in their career and is looking for ways to save money on healthcare costs. They may be on a tight budget and may be looking for ways to reduce their out-of-pocket expenses.
2. The Family: This customer is a family with multiple members who need to be covered under a healthcare plan. They are looking for a plan that will provide the best coverage for their family at the lowest cost.
3. The Senior: This customer is an older adult who is looking for ways to save money on healthcare costs. They may be on a fixed income and may be looking for ways to reduce their out-of-pocket expenses.
4. The Student: This customer is a student who is looking for ways to save money on healthcare costs. They may be on a tight budget and may be looking for ways to reduce their out-of-pocket expenses.
5. The Self-Employed: This customer is a self-employed individual who is looking for ways to save money on healthcare costs. They may be looking for ways to reduce their out-of-pocket expenses and may be looking for a plan that will provide the best coverage for their needs.

What are different customer persona for bank loans
1. The Young Professional: A young professional who is looking to purchase a home, car, or other large purchase and needs a loan to do so. They are looking for a loan with competitive interest rates and flexible repayment terms.
2. The Small Business Owner: A small business owner who needs a loan to finance their business operations. They are looking for a loan with low interest rates and flexible repayment terms.
3. The Retiree: A retiree who is looking for a loan to supplement their retirement income. They are looking for a loan with low interest rates and flexible repayment terms.
4. The Student: A student who is looking for a loan to finance their education. They are looking for a loan with low interest rates and flexible repayment terms.
5. The Investor: An investor who is looking for a loan to finance their investments. They are looking for a loan with low interest rates and flexible repayment terms.

How to build data across online and offline the data engineering blueprint
1. Identify the data sources: Identify all the available data sources, both online and offline, that you need to build your data engineering blueprint. This includes data from websites, databases, APIs, mobile apps, and other sources.
2. Collect the data: Collect the data from the identified sources and store it in a secure location. Depending on the type of data, you may need to clean and transform the data before storing it.
3. Create a data model: Create a data model that will allow you to store, access, and analyze the data. This model should be designed to accommodate the data sources you have identified.
4. Create a data pipeline: Create a data pipeline that will allow you to move data from the data sources to the data model. This pipeline should be designed to be efficient and secure.
5. Create a data warehouse: Create a data warehouse that will store the data from the data pipeline. This warehouse should be designed to be secure and scalable.
6. Create a data visualization layer: Create a data visualization layer that will allow you to visualize the data in the data warehouse. This layer should be designed to be user-friendly and interactive.
7. Create an analytics layer: Create an analytics layer that will allow you to analyze the data in the data warehouse. This layer should be designed to be powerful and flexible.
8. Create a reporting layer: Create a reporting layer that will allow you to generate reports from the data in the data warehouse. This layer should be designed to be easy to use and customizable.

What are different data engineering challenges to build customer 360
1. Data Collection: Collecting customer data from multiple sources and in different formats.
2. Data Integration: Integrating customer data from multiple sources into a single unified view.
3. Data Quality: Ensuring data accuracy and completeness.
4. Data Analysis: Analyzing customer data to gain insights and uncover trends.
5. Data Visualization: Visualizing customer data to make it easier to understand and interpret.
6. Data Security: Ensuring customer data is secure and protected from unauthorized access.
7. Data Governance: Establishing policies and procedures to ensure data is managed and used responsibly.

Keep Exploring!!!

January 28, 2023

Hyper-Local - Emerging Retail Trend

  • Hyper-Local Food is the conscious decision to buy food that is grown very close to where you are currently living. 
  • These foods will typically be grown and created by your local farmer or rancher.
  • Incentivize your local farmers and small businesses
  • Definition of real food is no ingredients labels - just the single source ingredient itself.

Ref - Link

Keep Exploring!!!

December 30, 2022

Retail Product Detection

Ref - Post 

  • Product region, brand logo region
  • Product textual data (title, brands)
  • The regions of interest in images were detected by a pretrained teacher model
  • Following the trend of using free-form text, we train the CPG model with 2.3M product entities synthesized from an e-commerce site in a self-supervised fashion
  • The bounding boxes for product-noun-to-object task are generated by a pre-trained general domain modulated detection model
  • Visual-language understanding of logos, brand strings, product details for the query product entity and for all brand representative product entities


  • Text to image lookup and comparison
  • Similar embedding lookup and comparison


  • Crafted image caption is tokenized and encoded using a pre-trained text encoder: RoBERTa
  • Image and textual features are concatenated as a multimodal vector and fed to a joint transformer encoder with cross attention between image and textual features
Keep Exploring!!!

Vision and Retail / LEGO

 





  • Manual process to automated process
  • High-quality image checks
  • Better attention-based models





Ref - Link

Keep Exploring!!!

April 16, 2022

Vision Use cases - Self Checkout

Product - Mashgin

  • Detect, Identify and Pay
  • Came Angle - Top View
  • Extract at least one feature from the images, and recognize the object based on a predetermined model being applied to the extracted feature from the images.
Self Checkout Vendors List1, List2

Product - Zippin

  • Scan from your Phone
  • Overhead Camera
  • Shelf Level Sensors
  • Billing based on RFID / Other methods Tags 
How it works - Link
  • Overhead cameras follow customers' movements as they move around the store—without using face recognition - Maybe Phone Signals
  • Cameras and smart shelf sensors track when and which products are picked up or put back. - Weight sensors
  • Combining these two inputs allows Zippin to place the right items in the right shoppers' virtual carts. - Phone + Shelf Activity
  • On leaving the store, customers receive a receipt detailing their charges. Watch this video to see Zippin in action.
My Feedback - It is a combination of Tech, It could be weight sensors + RFID + Vision. One key takeaway is to look at each tech as a complementary tech. I usually see only Vision-based / RFID-based. True value comes not by replacing one with another but by bringing and leveraging the best out of all tech.

Keep Exploring!!!

December 28, 2021

Retail Trends 2022 Report

Key Notes
  • Data collection from devices
  • Insights shared for Retail Locations in US
  • Positive Trends end of year
  • Positive growth in physical retail




  • Traffic up since october for holiday traffic
  • 2022 will see more in Home improvement category
  • Heavy investment in online, supply chain technology
  • Physical stores also expanding for online brands
  • Touch and feel,Product Experience
  • Services for better relationships / get customers back
  • Healthcare is growing
  • Smaller format stores (Sephora / Kohls / Target)
  • Grocery did well in 2021
  • Hyperlocal has picked up

Keep Exploring!!!

September 25, 2021

Planogram Notes

 Session #1

  • Brand / Distributor has to plan their store space
  • Limited space / Short product life cycle / competition
  • Increase sales - Right products on the shelf
  • Space management and Visual merchandising
  • Catalog / Products
  • Merchandise displayed with signage, Setup, Planogram execution, stocking, maintaining, restocking
  • Maximize sales, Increase volumes
  • Before and After Images (After Restock)
  • Rotation of products

Key Notes
  • Planogram - Product Placement Strategy. 
  • Shelf - Distance between shelves, Height of shelf, Number of Isles
  • Visual placement, alignment with software


  • Goal of planogram
  • Grab attention from customers
  • Adding incremental products
  • Merchandising Techniques
  • Top shelf - Regional brands, smaller brands
  • Second shelf - Bulls eye - Best Sellers
  • Bottom Shelf - Bulk items, Heavier products

  • Find Categories and their sales distribution

  • Color complementing approach



Session #2


  • Each Store
  • Each Article
  • Each Season




Session #3


Key Notes
Consumer Decision Trees






Keep Thinking!!!

August 16, 2021

Forecasting Reads - Research papers - Retail

Paper #1 - An industry case of large-scale demand forecasting of hierarchical components

Key Notes

  • Demand forecasting system of electronic components in manufacturing
  1. Algos leveraged - 1) Adaboost, 2) ARIMAX, 3) ARIMA, 4) Bayesian Structural Time Series (BSTS), 5) Bayesian Structural Time Series with a Bayesian Classifier (BSTS Classifier), 6) Ensemble of Gradient Boosting (Ensemble), 7) Ridge regression (Ridge), 8) Kernel regression (Kernel), 9) Lasso, 10) Matrix Factorization from section VII (MF), 11) Neural Network (NN), 12) Poisson regression (Poisson), 13) Random Forest (RF), 14) Support Vector Regression (SVR).

  • Techniques on 1) data pre-processing, (2) prediction, and (3) model selection 
  • Symmetric Mean Absolute Percent Error (SMAPE) serves to evaluate the performance of the models

Paper #2 - Learnings from Kaggle’s Forecasting Competitions

Key Notes

  • High-frequency series at weekly, daily, and sub-daily levels
  • Frequency data in the form of weekly, daily and hourly data
  • Three full seasonal periods were required at each frequency  i) complex vs. simple models, ii) crosslearning, iii) prediction uncertainty and iv) ensembling
  • Walmart Store Sales and the Rossmann competitions
  • Sales by store/department/week and store/day
  • Forecasts of unit sales being required by product/store/day

Data Preprocessing

  • Set NA or Negative values to zero.
  • Remove time series with all zero values. 
  • Remove leading zeros.
  • To calculate the feature vectors, we use the R package feats
  • Apply principal components for dimensionality reduction using the prcomp algorithm


  • Most of the top performers used ensembles of global XGBoost models to create forecasts, but a few of them did include local XGBoost models as part of their ensemble
  • Holidays and promotion, turned out to be essential for obtaining high performance in this competition
  • Global ensemble models outperform local single models

Feature Extraction

  • Day of Week
  • Weekend
  • IsHoliday
  • Ispromotionday
  • IsMonthEnd
  • IsyearEnd
  • IsQuarterEnd
  • IsLocalHoliday
  • WeekofYear
  • Wolling Window
  • Average of 2 - 3 - Weeks
  • Moving Average Numbers
  • Mean Every 2 Weeks
  • Incremental Differences Everyday
  • Adding Averages / Means - Weekly Average, Daily Average

Paper #3 - An Empirical Analysis of Feature Engineering for Predictive Modeling

Following sixteen selected engineered features:

  • Counts
  • Differences
  • Distance Between Quadratic Roots
  • Distance Formula
  • Logarithms
  • Max of Inputs
  • Polynomials
  • Power Ratio (such as BMI)
  • Powers
  • Ratio of a Product
  • Rational Differences
  • Rational Polynomials
  • Ratios
  • Root Distance
  • Root of a Ratio (such as Standard Deviation)
  • Square Roots
  • Counts - count engineered feature counts the number of elements in the feature vector that satisfies a certain condition
  • Statisticians have long used logarithms and power functions to transform the inputs to linear regression

Paper #4 - VEST: Automatic Feature Engineering for Forecasting



  • sku,wkno,saleqty
  • cluster and forecast
  • DWT - Dynamic Time Wraping Metric for clustering timeseries
For offline Retail Stores my list of feature variables

Store level stats
  • Date
  • StoreId
  • Items in Store
  • Traffic Count
  • Holiday / Festival
  • Number of Item Categories
  • Weather
  • Out of Stock Items
  • Cost of Products, The price value of SKU
  • Promotional Offers / Seasonal Information
  • Weather Information on Store on that Day
  • Store operational timings
  • Store Labour Details
Data Product Thinking
  • With 20% more restock of this item, It might reduce 10% out of Stock, 5% improvement in Traffic (Instead of blind forecast provide a collated recommendation)
  • With 20% reduction in tomorrow traffic, corresponding items or % of Sale Can be presented
  • Multiple models will run behind these decisions to generate the recommendations
More Reads

Keep Thinking!!!

July 17, 2021

RetailVisionWorkshop2021 Notes

 Links 

Key Notes
  • Physical stores are becoming digital
  • Products more easily searcheable
  • Better experiences at stores
  • Minimize loss of sales
Use cases
  • Product Detection Challenges
  • Pricing challenges based on data
RetailVisionWorkshop2021 Pricing Challenge - Ehud Barnea
Key Notes
  • Price from bounding boxes
  • Remove promotion content and read price content
  • Country differences
  • Winning Solution
Dataset Features

RetailVisionWorkshop2021 - Gang Hua



  • 360 degree camera to scan everything in store
  • 3D construction of motion structure reconstruction
  • Shelf detections in 360 cameras
  • Identify Shelf level information
  • Optimal robot position to capture shelf images
  • Create Digital twin duplicate product


  • Assortment planning for online vs offline






06 RetailVisionWorkshop2021 - Sean Bell
Detection, Features, Character Embedding



  • Large scale embedding for product recognition







Loss Functions
  • Anchor image
  • Distances corresponding to same product
  • Same vs Different products
  • ArcFace Loss
  • Every product has centres
  • Compare anchors and centres


Combination of Vision + Word Embedding for product categorization

GeM Pooling
  • Feature map at top of Network
  • Average over spatial dimensions
Product Recognition



07 RetailVisionWorkshop2021 - Aviv Eisenschtat




  • Dynamic Shelf Reality
  • New Visual designs of products



  • Combination of techniques
  • Similar products
  • Product Category
  • Clustering for similar images








Keep Collecting Ideas!!!!

Keep Learning!!!