Susan Walsh - The Classification Guru

Fixer of dirty data ★ Spend data classification, supplier normalisation, and taxonomies ★ DataIQ100 x 2 ★DataIQ Data Champion 2022★ Author "Between the Spreadsheets" ★ Creator of COAT ★ TEDx - say NO to NO ★ DataVenger

I’m Susan Walsh, also known as The Classification Guru, a globally recognised expert in spend data classification, cleaning, and transformation. For over a decade, I’ve helped organisations fix dirty, unreliable data and turn it into insight they can actually trust.

In 2017, I founded The Classification Guru Ltd, rebuilding my career from the ground up after coming back from bankruptcy after my first business failed. What started as a solo consultancy has grown into a specialist business supporting 100+ organisations globally, particularly in procurement, sales, and marketing, where clean data underpins reporting, automation, and AI.

I work with mid-sized and enterprise organisations, consultancies, and technology providers that rely on complex, high-volume data but struggle with inconsistency, duplication, and poor structure. My clients include procurement, finance, sales, and marketing teams who need data they can stand behind, whether that’s for spend analysis, supplier management, CRM reporting, forecasting, compliance, or AI initiatives.

Keeping a business alive and growing for almost nine years hasn’t been about shortcuts or hype. It’s been built through real-world delivery, practical problem-solving, and a refusal to accept “good enough” data as acceptable. Along the way, I’ve developed frameworks and tools to help organisations embed sustainable data quality, including the COAT framework (Consistent, Organised, Accurate, Trustworthy) and Samification, a self-service supplier normalisation platform launched in 2024 to make clean, structured data accessible at scale.

I’m also an active contributor to the wider data and business community. I’m a TEDx speaker, international conference speaker, and recognised thought leader in data quality and classification. I’ve authored three books, including Between the Spreadsheets 1st and 2nd editions, and the upcoming Optimizing Sales and Marketing. I teach globally via platforms such as Pluralsight, O’Reilly, and the Analytics Institute. Through consistent, practical thought leadership, I’ve grown an engaged LinkedIn audience of 43,000+ professionals.

Alongside my commercial work, I founded the Women Who Speak LinkedIn group, a free initiative connecting women speakers with event organisers to improve visibility and representation. I hope my journey shows that you don’t have to fit a mould to build a credible business, lead in your field, or create meaningful impact.

My mission is simple: help organisations move from spreadsheet chaos to clean, organised, trustworthy data that actually works.

Founder/MD (Mistress of Data)

I love improving the quality of procurement spend data, giving teams clarity so they can make better business decisions and cost savings.

Why not let me take the pain out of laborious data issues and make your life easier?

Whether it's a small or large data set, the accuracy can be improved by identifying classification errors, conflicts or gaps. I can provide a data verification service to efficiently find and correct these in a fraction of the time it would take you or a team member.

And a crucial part of having accurate data is also working with a comprehensive taxonomy, something that can be easily overlooked. I can provide a taxonomy development service to ensure you have all the vital areas covered for the greatest visibility - job done!

If you struggle with the time, resources or willingness to tackle your data, why not get in touch to see how I can make your life easier.

Who does quiet, easing back into work in January? Not me!

Just had a wonderful evening up in London meeting Adita Karkera, Ph.D. and lots of fabulous ladies from Women In Data™️

Gonna need a lie in tomorrow now 🤣🤣

Thanks Shubhangi Goyal for organising and Samir Sharma for being an honorary woman in data! 

The Classification Guru Ltd Samification

Susan Walsh

No alternative text description for this image

Ok 2026, I may not be ready, but let’s do this!

When you work for yourself there’s very few h&s measures in place, like a warm workplace.

I woke up to -4 outside and not much different inside, even with the heating on, so whoever gets on call with me today will find me like this. #sorrynotsorry

The Classification Guru Ltd Samification

It's baaaack!  That's right, lipsyncsunday is back in 2026, and this is the energy I'm bringing into 2026 - bad vibes we tell them bye bye!

And not just that, after years of resisting, I've now set up a TikTok account @classificationguru so give it a follow if you want even more crazy, and of course some great data tips, eventually...

What energy are you bringing into 2026?  

Oh and good luck in your first week back, take it easy!

The Classification Guru Ltd Samification

I asked ChatGPT one question: "Based on our interactions, how could I be leveraging you more?"

Because I want to work smarter, not harder this year.

And the answer wasn't, “write more posts faster," it was slightly unexpected - AI works best before things are polished, not after.

Which basically means that even with AI, I'm still a control freak, not delegating until the last minute, so that's something I'll be working on this year.

Here’s the recommendations I'll be taking forward:

 • Using it as a thinking partner, not just a writing tool
 • Pressure-testing ideas before they’re fully formed
 • Acting as an editor with opinions, not just a spellchecker
 • Repurposing one solid idea into multiple formats
 • Being a built-in “so what?” detector
 • Exploring bolder positioning without committing to it publicly
 • Preparing for talks, panels, and conversations earlier, not at the last minute

The biggest shift for me? Bringing AI in when things are messy, not when they’re “ready”. Drafts, fragments, half-formed opinions… that’s where the real leverage is.

So tell me, where in your workflow could AI take more of the heavy lifting, so you stay in your zone of genius? 

Why not try this prompt or a variation and let me know!

The Classification Guru Ltd Samification

Have you met the Dirty Data Villains?

Every dataset has them.
Some are obvious. Some hide in plain sight.
Together, they’re responsible for broken reports, failed joins, messy dashboards, and far too many “why doesn’t this match?” moments.

Here’s the current Dirty Data Villains lineup 👇

🟡 Rogue Punctuation
Commas, apostrophes, periods, and symbols turning up where they don’t belong. Breaking imports, splitting values, and causing errors that are frustratingly hard to spot.

⬜ Sneaky Spaces
Invisible troublemakers lurking at the beginning or end of values. The reason your “exact matches” aren’t exact and your duplicates refuse to reveal themselves.

👯 Duplicate Dan
The master of cloning. Same customer, same supplier, same invoice… entered twice (or more), often with just enough variation to avoid detection.

🔤 Typo Tracey
One wrong letter is all she needs. Misspellings, swapped characters, missing letters — causing failed lookups, bounced emails, and embarrassing mistakes.

📅 Format Fred
The chaos king of inconsistency. Dates, phone numbers, and text fields all formatted differently across systems, making automation and reporting painful.

💥 Why they matter
These villains don’t just make data messy; they undermine trust. And without trust, data can’t be relied on for decisions, insights, or AI.

The good news?
Once you can name them, you can spot them.
And once you can spot them, you can clean them.

More villains may be lurking… but for now, this is your most wanted list.  And if you need some help identifying them, ask me about our new data diagnostic service, more details coming soon!

Which Dirty Data Villain causes you the most pain?  And who would you add?

📘 Two books
📉 Big discounts
📊 Cleaner, calmer, more trustworthy data

Get more Susan for less!

🟣 Between the Spreadsheets from Facet Publishing – 20% off using NEW20
🔴 Optimizing Sales & Marketing Data from Kogan Page Publishing – 40% off with SALE40

What you’ll actually learn:

💡How to spot dirty data before it wrecks reporting
💡Practical ways to fix duplicates, inconsistencies, and naming chaos
💡Why “the tech will fix it” usually doesn’t
💡How to build data you can trust for decisions, automation, and AI
💡Real-world lessons from projects, not fluffy theory

If you’re wrestling with messy data, unreliable dashboards, or a CRM that feels held together with hope and pivot tables, these will save you time, frustration, and a few awkward meetings.

Built on real client work. Powered by the COAT framework. Zero nonsense.

Grab them while the discounts are live!

Shoutout to some fellow authors Jordan Morrow Tiankai Feng Nicola Askham Caroline Carruthers Kristen Kehrer Roberto Maranca Albert Bellamy Keith McCabe (MCIPS) Samir Sharma Dr. Joe Perez

The Classification Guru Ltd Samification

I create content about deep learning | The DevRel and Deep Learning Dude

Hacking on LLMs, curating multimodal datasets, and writing a book about RAG.

Harpreet Sahota 🥑

i've literally been waiting for years to have an OPEN SOURCE model like qwen3-vl-embedding

i tested its multimodal retrieval capabilities on a corpus of 412 short video clips and the results literally blew my mind

here are the queries i tested:

1. a cartoon guy drinks merlot wine

i like this query because we see how it can retrieve based on semantics (a cartoon), text (the label merlot), and temporal action in the video (the cartoon guy drinks the wine mid-way through the video)

2. garfield runs out of the door

semantics are awesome here, the model knows i'm talking about the cartoon character...

3. a woman in a blue dress sleeping on a red bench

the skeptic in you might think that it's retrieving just based on the red color block in the 2/3 of the video...but notice the specific part of the query "a woman in a blue dress..." and this is only shown in 3s out of the full 10s

this is such a huge release 

and it's gonna open up SO much more for multimodal video retrieval this year

on my wishlist is natural language search of pcd datasets, who gonna ship that?

you can hack around with the model using the resources below

check out the docs: here: https://lnkd.in/gh7yfBNP

and the quickstart nbhere:  https://lnkd.in/gbinsx7p

🤖 Hacker-in-Residence @ Voxel51| 👨🏽‍💻 AI/ML Engineer | 👷🏽‍♀️ Technical Developer Advocate | Learn. Do. Write. Teach. Repeat.

for those who missed it, or were there in-person and know the trouble i was facing 😆, my ODSC webinar is now live on youtube!

in this session i discuss visual ai techniques for automotive damage detection. 

i used the cardd dataset, which is a public dataset built specifically for vehicle damage analysis and demonstrated how fiftyone helps you explore, visualize, and build models to detect dents, scratches, cracks, glass shatter, tire flats, and broken lamps.

i feel like its a super practical workshop with some insightful workflows for visual AI in automotive settings, but as the creator i might be biased.

only one way to find out for yourself, watch the webinar!

https://lnkd.in/ewfz5vZD

Open video: Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota on youtube.com

Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota

sometimes i look back at the shit i get done and i genuinely impress myself

how teams really build Visual AI in the wild? what's the he messy reality?  

i don't know...and maybe its because nobody’s asking practitioners and compiling their answers so we can find out the landscape actually looks like. 

so, we at Voxel51 are kickin off the...

wait for it...

 State of Visual AI survey...vey...vey

for those out ther building visual AI systems i want your hot takes

what’s the hardest part about making visual ai a reality? 

let us know in this survey

it'll take you 30 minutes and is a much better use of time than baby sitting your runs and staring at your loss curves

i can't offer much beyond my heartiest thanks, but you will get early access to the full report with benchmarks, common pain points, and where you stand within the landscape. 

here's a link: https://lnkd.in/gnsADACy

MedGemma 1.5 supports detection, but for best results, you'll need to fine-tune. 

there's a kaggle competition using the model, i created a starter notebook to give you a jump start on how to fine-tune it for detection

checkout the starter notebook and additonal resources 👇🏼

cc Omar Sanseviero Megan Risdal Logan Kilpatrick

looking forward to the next meetup in boston!

Join our in-person meetup at the Microsoft Research Lab at the Massachusetts Institute of Technology in Boston, Massachusetts on Feb 18 to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Register here: https://lnkd.in/gi4kpSMB

Talks will include:

• SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

• Culturally Adaptive AI - Anku R. at Massachusetts Institute of Technology

• Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

• Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at Massachusetts Institute of Technology

• Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

#computervision #ai #artificialintelligence #machinevision #machinelearning #datascience

Syed Abdul Sami Rizvi, Matthew Ebisu and 118 other attendees

View event: Feb 18 - Boston AI, ML and Computer Vision Meetup

Feb 18 - Boston AI, ML and Computer Vision Meetup

in the asu area and wanna get started with open source contributions? then don't miss this hack

On March 21, 2026, we’re hosting Agents World: Visual AI Hackathon @Arizona State University, together with Pavan Turaga 🚀 

This is a hands-on day: meet people, build with AI, eat pizza, and leave with something you created after a short workshop and a full day of hacking. 
You’ll work with the FiftyOne ecosystem and real models used in practice, like Qwen, Gemini Vision, Sharp, and more. 

If you’re an ASU student who wants to build, learn by doing, and work with real Visual AI tools, this is for you.

Registration is open:
https://lnkd.in/gBCHW5Fg

Hope to see you at ASU. I’ll be there with the amazing Voxel51 team:  Sid Mehta, Ritchie Martori, Jimmy Guerrero ! 🙌

Inspired by the amazing Hugging Face’s 2025 AI Timeline, we created one for the Fiftyone community. The FiftyOne Community Development Timeline highlights more than 131 contributions from 2025, including datasets, models, plugins, and integrations.

You can filter by type or modality and jump straight to each integration.
https://lnkd.in/ev2kpCGN

Big thanks to the entire Voxel51 community for building all of this together.
Harpreet Sahota 🥑, Daniel Gural, Paula Ramos, PhD, Jimmy Guerrero, Derek Van de Streek, Nicholas Lotz 🚀

Gonna be a great series of talks, lots of technical depth!

Chief Community Officer @ Voxel51 | Startup Advisor

Join us on Feb 18 for the Boston AI, ML and Computer Vision Meetup! Pre-registration is mandatory to clear building security - https://lnkd.in/gHtBuH49

Talks will include:

* SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

* Culturally Adaptive AI - Anku R. at MIT

* Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

* Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at MIT

* Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

***********

Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place.

“pip install fiftyone” is all it takes to get started - https://docs.voxel51.com/

#computervision #ai #artificialintelligence #machinevision
#machinelearning #datascience #physicalai

taplio

The Battle

Susan Walsh - The Classification Guru

Harpreet Sahota 🥑

Followers

Posts

Engagements

Likes

Performance ScoreSusan Walsh - The Classification Guru's LinkedIn Performance

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Susan Walsh - The Classification Guru

Harpreet Sahota 🥑

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Susan Walsh - The Classification Guru's LinkedIn Performance

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreSusan Walsh - The Classification Guru's LinkedIn Performance