Sorting through hundreds of thousands of datasets is no easy task, but the Sensibill Data Lab is up to the challenge!

Hi 👋  My name is Priyanka and I’m a Product Data Analyst in the Sensibill Data Lab. When I was completing my Master of Business Administration, I fell in love with everything about data; how to understand algorithms, find trends, and figure out how to apply it to different business use cases. Luckily for my data-loving self, this all applies perfectly to my role in the Sensibill Data Lab! 

Meet the Sensibill Data Lab 🤝

The Sensibill Data Lab is a team of in-house data scientists dedicated to providing transparent and accessible insights about consumers’ actions to drive growth and personalization at scale for Sensibill’s clients. If you’re looking for the “data nerds,” you’ve found the right place 🤓 We’re all driven by a thirst for knowledge, and data is a great foundation to start. Data can seem overwhelming and clunky, but with the help of correct data science algorithms and data analysis techniques, we can uncover insights that help us paint a story.

In our day-to-day, we are focused on analyzing millions of data points streaming in every single hour. Leveraging our cloud-native, machine learning-powered Sensibill data platform to access and analyze the SKU-level data, we classify and categorize data into profiles to derive meaningful and actionable insights. 

I help the team put together hundreds of thousands (!!!) of data sets so that we can look for trends and give data a visual identity. Think of it as putting together a bunch of puzzle pieces to get a full picture. On their own, a puzzle piece might not give you an idea of what the ending picture looks like but combined with others, you can start to get a clearer image. 

We sort through how much data?!

Here’s a quick snapshot of the breadth of data our team has access to:

• 220k merchants processed worldwide

• 96% coverage of top 100 US merchants

• 96% coverage of top 100 Canadian merchants

• 93% coverage of top 100 UK merchants

• 25m line items extracted

• 14m SKUs/UPCs extracted

• 4m unique SKUs/UPCs extracted

• 150+ number of extracted fields

• 415m total product catalog 

• 6000+ unique product categories

This number will only continue to grow as we partner with more companies and as consumers continue spending more.

What makes SKU-level data special and different?

Unlike a shopper panel where people are paid for their receipt uploads, the receipts we see come from usage “in the wild,” if you will 🌿 These are receipts from people who are making purchases and then tracking their spending; they are not just making purchases to get the receipt. This makes our data sources unbiased and more reflective of everyday purchase behavior, not just behavior driven by promotions. The SKU-level data is a great complement to any other market data you’re collecting or purchasing. 

So, why do you need access to the SKU-level data? With the rise of online shopping, especially during the pandemic, a lot of retailers are broadening the product categories they offer. Stores are steadily becoming general retailers that are resellers for other products that their customers might be interested in purchasing. 

For example, in the US, the retailer Barnes & Noble is known as a book store but has been adding to its catalog of items. They now sell a lot more than just books: toys, candy, electronics, clothing accessories, homeware, etc. Because of the variety of items available, FIs cannot assume that someone with a receipt from Barnes & Noble is strictly buying books. 

Through knowing what people are actually purchasing on an item level, FIs can start to better understand what people value and prioritize; not just when and where they purchase. 

Putting all this data into practice 

The Sensibill Barcode Report is a great example of how we can surface timely and relevant insights on everyday spending. We are reporting on what we are seeing consumers spending on so that our readers can make data-informed decisions or use this to complement other data they are looking at. In my next blog post, I will share the process of how we build our Barcode Report, so stay tuned! 👀

Keeping your data safe 🔒 

Data security is critical for every FI and is just as important to Sensibill. We never sell users' personal data. Any insights given publicly, like in the Sensibill Barcode Report, are always represented as aggregate trends, eliminating the possibility of ever linking SKU data to a specific individual. We understand the importance of privacy and security, especially now, and we take that seriously.

Check out the latest Sensibill Barcode Reports

• The May Barcode: Home improvement spend in the USA | in Canada

• The June Barcode: Consumer travel spend during the pandemic

• The July Barcode: Pet-related spend during the pandemic in Canada | in the USA

• The August Barcode: Consumer spend returning to normal

• The September Barcode: Beyond the 'Panic-Purchase' Mindset

• The October Barcode: The great apple VS pumpkin pie debate

• The November Barcode: Consumer spend signals “work-from-home” is here to stay

Our next Sensibill Barcode Report comes out in December! Want to get it directly in your inbox? 📧 You can subscribe here!

Priyanka Mukherjee
Product Data Analyst

While completing her Master of Business Administration, Priyanka fell in love with data. At Sensibill, she uncovers customer spend insights through algorithms, data analysis, and visualization. Outside of work, you can find Priyanka trialing a new recipe, watching a thriller on Netflix, or teaching her cat to do some new tricks!