Susan Walsh - The Classification Guru

The Classification Guru Ltd

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.

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.

Founder

Data Collaboration Alliance

I am a member of the Advisory Committee at the Data Collaboration Alliance, a nonprofit organization that’s dedicated to establishing CONTROL as the basis for meaningful Data Ownership and global Collaborative Intelligence. Our approach of eliminating data silos and copy-based data integration is similar to how societies already protect the value of their currency, identities, and intellectual property - and it works for data, too. My fellow advisors include the Executive Director of the Mozilla Foundation and the ex-CIO of Dropbox. I'm also a contributor to the Data Collaboration Community which offers open datasets, free tools, and free training in the data-centric skills of the future. Visit: https://www.datacollaboration.org/community

Advisory Committee / Instructor

Facet Publishing

Dirty data is a problem that costs businesses thousands, if not millions, every year. In organisations large and small across the globe you will hear talk of data quality issues. What you will rarely hear about is the consequences or how to fix it.

Between the Spreadsheets: Classifying and Fixing Dirty Data draws on classification expert Susan Walsh's decade of experience in data classification to present a fool-proof method for cleaning and classifying your data. The book covers everything from the very basics of data classification to normalisation, taxonomies and presents the author's proven COAT methodology, helping ensure an organisation's data is Consistent, Organised, Accurate and Trustworthy. A series of data horror stories outlines what can go wrong in managing data, and if it does, how it can be fixed.

After reading this book, regardless of your level of experience, not only will you be able to work with your data more efficiently, but you will also understand the impact the work you do with it has, and how it affects the rest of the organisation.

Written in an engaging and highly practical manner, Between the Spreadsheets gives readers of all levels a deep understanding of the dangers of dirty data and the confidence and skills to work more efficiently and effectively with it.

Author - Between the Spreadsheets

CONSTELLIA LIMITED

Connecting Professional Services Procurement people to the Consultancy Procurement Council

Membership Manager

Simfoni

+ Lead spend analytics project delivery across Europe & Middle East
+ Project Implementation​
+ Delivery of product demos
+ Development and delivery of training for Analytics team
+ Product development support
+ Spend analytics
+ Taxonomy development​

Senior Analytics Project Lead - Europe & Middle East

Highways England

Project Support Officer

Philips

Data Verification

+	Administration of product database
+	Working with cross functional teams to resolve issues
+	Develop and deliver training for business hubs to improve processes

Data Product Researcher

Coupa Software

+	Project managing multiple projects simultaneously ensuring all were delivered within time and on budget
+	Management of a team of 14 QA staff
+	Developed and implemented training plan and best practice documents
+	Recruit and train new staff
+	Ensuring consistent quality of work  produced by team

QA Manager

Spend360

+	QA, classification and review of data
+	Excellent attention to detail
+	Managing workload to tight deadlines

Data Services -QA

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

Are you struggling to get reliable insights from your data?  Do you have duplicates, multiple versions of the same supplier or customer, and multiple date and address formats?  And is it saved in multiple different systems?

The Classification Guru can help.

If you’re in procurement, do you find it hard to see how much you are really spending with one supplier, and on what?  Have you got free text descriptions which mean you have multiple versions of the same item, often misspelt and not against the correct GL or categorisation? How can you make the best negotiations with your suppliers, the biggest cost savings, or manage your supplier list if you don’t have the correct information?

Or if you work in sales or marketing, is your CRM full of junk data, poorly formatted and even missing information, and maybe saved in multiple different systems?  Your team could be wasting time contacting redundant leads, or worse you could be sending out expensive print out to the same address twice, or addresses that don’t even exist.

We bring clarity and accuracy to data and help teams work more effectively and efficiently, finding cost savings through spend and time management, supporting better, more informed business decisions, delivering a strong ROI and delivering back to your organisation faster and more cost-effectively than using large consultancies or spend analytics providers.

While most people dread having to classify or cleanse data, my team and I love it! We are hugely passionate about providing clients with accurate and meaningful data, and because I have been doing this for a decade, I can do this much faster and more accurately than people who might look at their data infrequently.

We can help prevent costly mistakes from happening.

There are many solutions available to automate data classification, but these are never 100% accurate. I've developed a method that my team use to efficiently and accurately classify, cleanse and verify data to minimise the errors in the same amount of time.

When working with large volumes of data it's hard to spot these errors even if you know what you're looking for and especially in Excel, let alone if you don't. With my team and I’s knowledge, experience and tools we can do this for you, freeing up your internal resources.

Fix your dirty data now - www.theclassificationguru.com

Voxel51

• Explore, tinker with, and push the boundaries of the latest AI and machine learning technologies to showcase what's possible with open-source tools and frameworks

• Build inspiring prototypes, proof-of-concepts, and example applications that demonstrate creative and impactful uses of AI to the developer community

• Contribute meaningfully to the open source ecosystem by creating and maintaining libraries, tools, datasets, tutorials and guides that enable developers to more easily leverage AI capabilities

• Curate, clean, annotate and publish unique multimodal datasets spanning text, images, audio, video, 3D and other emerging data types to facilitate novel machine learning research and applications

• Create engaging technical blog posts, social media content, videos, and presentations that educate and inspire developers and data scientists to build with AI

•  Collaborate openly with our internal teams and the broader AI/ML community to cross-pollinate ideas, share knowledge, and collectively advance the state-of-the-art

• Evangelize our technology and vision by representing the company at hackathons, conferences, meetups, universities, and other developer-focused events

•  Influence the product roadmap by providing input on the developer experience, uncovering opportunities for new features and improvements based on community feedback and your work

• Continuously learn, experiment with, and provide feedback on beta versions of our latest models and capabilities to help shape the future of our platform

Hacker-in-Residence

LinkedIn

1) Introductory computer vision course for LinkedIn Learning

2) Prompt Engineering with LangChain (releasing March 2024)

3) RetrievalAugemnted Generation with LlamaIndex (releasing Q2 2024)

4) Fine-tuning LLMs with Hugging Face TRL (est release Q3 2024)

5) Text Generation with Hugging Face Transformers (est release Q3 2024)

LinkedIn Learning Instructor

The Artists of Data Science

The ONLY personal growth and development podcast for Data Scientists

Host

Deci AI

Developer Relations Manager

Pachyderm Inc.

Senior Developer Advocate

Comet

ML Developer Advocate

Data Science Dream Job

Principal Data Science Educator

Price Industries

Lead Data Scientist

Bold Commerce

Senior Data Scientist

Emergent BioSolutions

Biostatistician

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 🥑

sam3 is seriously a step change improvement over sam2

the model is seriously good, glad they brought back text prompts. the automatic segmentation isn't as good as i hoped it to be...but it still works quite well. 

i also got it to output image embeddings and that was cool to visualize in the app

learn more here: https://lnkd.in/gzqJzj6G

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

qwen3vl is literally the best model i've used for video usecases. blows my mind

hosting a virtual event tomorrow about document ai

you may or may not find it interesting, but i guarantee you'll learn something

join me here: https://lnkd.in/dFXPimVc

sony ai released a pretty cool dataset called the fairness human centric image benchmark, super high quality labels

instructions for downloading and parsing the dataset into fiftyone format can be found here: https://lnkd.in/g_VwxJx4

physical AI is top of mind as the next frontier for deep learning. but it'll only succeed if you have good datasets

language models scaled with web-scale text. 

vision models got ImageNet. 

now Voxel51 and NVIDIA are trying to do the same thing for physical AI 

autonomous vehicles, humanoid robots, anything that moves around atoms.

building these systems means millions of hours of testing in high-fidelity sims before you can actually deploy anything. 

petabytes of multimodal sensor data from various modalities

 LiDAR, cameras, radar, IMUs. 

but over 50% of simulations end up completely unusable because the input data is bad.

even small calibration or timing errors between sensors cascade through your neural reconstructions. 

you waste weeks and burn through millions in compute costs before you realize what went wrong.

the new FiftyOne Physical AI Workbench. it integrates with NVIDIA Omniverse and NVIDIA Cosmos and basically sits at the start of your sim pipeline to validate, clean up, and prep your multimodal data before it hits neural reconstruction and synthetic data generation.

what it does:

- automatically audits physical AI inputs across 75+ critical checkpoints

- transforms raw sensor streams into structured, searchable datasets

- triggers accurate neural reconstructions and generates synthetic scene variations

this means fewer wasted compute hours. 

iteration loops go from weeks to hours. 

you build safer, more reliable systems on data you can actually trust.

read more about what we've been building: https://lnkd.in/gC6_zn-X

i recently integrated 4 ocr models into fiftyone as remote zoo models these handle text extraction and document parsing. 

all available as remote zoo sources, you can get started with a few lines of code

different approaches for different needs:

1. mineru-2.5

1.2b params, two-stage strategy: global layout on downsampled image, then fine-grained recognition on native-resolution crops. 

handles headers, footers, lists, code blocks. strong on complex math formulas (mixed chinese-english) and tables (rotated, borderless, partial-border).

good for: documents with complex layouts and mathematical content

https://lnkd.in/dSwimdvp

deepseek-ocr

dual-encoder (sam + clip) for "contextual optical compression." 

outputs structured markdown with bounding boxes. has five resolution modes (tiny/small/base/large/gundam). gundam mode is the default - uses multi-view processing (1024×1024 global + 640×640 patches for details). 

supports custom prompts for specific extraction tasks.

good for: complex pdfs and multi-column layouts where you need structured output

https://lnkd.in/dhJn2h-v

olmocr-2

built on qwen2.5-vl, 7b params. outputs markdown with yaml front matter containing metadata (language, rotation, table/diagram detection). 

converts equations to latex, tables to html. labels figures with markdown syntax. reads documents like a human would.

good for: academic papers and technical documents with equations and structured data

https://lnkd.in/dNdTQYKg

kosmos-2.5

microsoft's 1.37b param multimodal model. two modes: ocr (text with bounding boxes) or markdown generation. automatically optimizes hardware usage (bfloat16 for ampere+, float16 for older gpus, float32 for cpu). handles diverse document types including handwritten text.

good for: general-purpose ocr when you need either coordinates or clean markdown

https://lnkd.in/dCTfGfV8


two modes typical across these models: detection (bounding boxes) and extraction (text output)

i also built/revamped the caption viewer plugin for better text visualization in the app: 

https://lnkd.in/dBebWdga

i've also got two events poppin off for document visual ai:

- nov 6 (tomorrow) with a stellar line up of speakers: https://lnkd.in/gkBEY4_r

- a deep dive into document visual ai with just me: 

https://lnkd.in/dFXPimVc

Open article: Document Visual AI with FiftyOne - November 14, 2025 by voxel51.com

Document Visual AI with FiftyOne - November 14, 2025

hype for this new integration, and proud of the team for shipping it at lightning speed. big ups to Daniel and AdonAI for goin beast mode on this one

🚀 Introducing Physical AI Workbench — integrated with NVIDIA Omniverse NuRec and NVIDIA Cosmos to solve the biggest bottleneck in physical AI.  

More than half of all physical AI simulations fail — not from bad models, but from bad input data. A timestamp off by milliseconds or a calibration drift of a few degrees can cascade through your neural reconstructions, leaving you with unusable results after weeks and millions in wasted compute. 

FiftyOne Physical AI Workbench sits at the start of your simulation pipeline and provides turnkey access to NVIDIA technology to ensure every simulation run begins with trustworthy data: 

✅ Audits 75+ critical checkpoints to ensure every reconstruction starts with validated inputs 
🎯 Enriches raw sensor streams into structured, searchable datasets 
🔗 Integrates directly with NVIDIA Omniverse and NVIDIA Cosmos for high-fidelity reconstruction and synthetic data generation. 

The result: an end-to-end workflow that prevents downstream failures — cutting iteration cycles from weeks to hours and eliminating GPU waste on failed reconstructions. We’re excited to see this workflow power autonomous vehicles NVIDIA DRIVE and robotics NVIDIA Robotics development teams move faster with higher accuracy. 

🔗 Read the full technical breakdown: https://lnkd.in/gTy5-TNF

taplio

The Battle

Susan Walsh - The Classification Guru

Harpreet Sahota 🥑

Followers

Posts

Engagements

Likes

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);}Harpreet Sahota 🥑's LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance