top of page


I’m an AI & machine learning consultant, and I help companies make the best use of today's machine learning technology in order to hit their KPIs. I analyze your data, build machine learning models, and show you how to be more data-driven, using resources you already have in order to reach your business goals. Whether your current pain point is conversion rate, fraud prevention, anomaly detection or any other - your data already knows what you need to solve it, and I can help you find out how.

Home: Text
Photo by CHUTTERSNAP on Unsplash


In the rapidly evolving alternative protein and FoodTech industry, effective R&D is crucial. I apply my expertise in machine learning and data science to accelerate and optimize R&D processes, fueling efficiency and innovation. From predictive modeling and experimental design optimization to the wide array of methodologies within machine learning, I equip your team with tools to fast-track product development, streamline prototyping, and enhance research outcomes. Harness the power of AI in your FoodTech R&D and turn your innovative ideas into sustainable, market-ready solutions faster.

Home: About


I’ve been working with data for over a decade, both in academia and in the tech industry. Prior to consulting, I worked for companies such as Armis and PayPal, utilizing big data and machine learning for fraud prevention, risk mitigation, and everything cybersecurity.

Today I work with both startups and more established companies, helping them use their data - and today’s AI & machine learning technology - to drive success. I have a special focus on the field of Alternative Proteins and FoodTech, though I still work with companies from all domains.

I also lead the Israeli community of Women in Data Science, utilize ML for whale preservation with the Deep Voice foundation, and offer my expertise with AI and data under the Good Food Institute mentoring program, as well as with the Modern Agriculture Foundation.

Home: About


I provide many services, some of which are:

1. Working with early-stage startups to refine their vision for incorporating AI into their product, and design both a short and long-term work plan.

2. Helping established companies understand the best ways to use their data in order to eliminate pain points and improve efficiency.

3. Building AI / ML systems to fit a specific need or requirement.

4. Mentoring junior data scientists and DS team managers, focusing on both the technical aspects of data science work, and the organizational challenges of implementing it into existing environments.

Home: Text



Founders of early-stage startups, who would like my (free) advice on their AI strategy.


Women-led startups, startups that focus on alternative protein / animal welfare, or founders who have signed with Founders Pledge.


Email me with a brief description of your mission, and what you hope to get from our session.

While I will not be able to accommodate everyone, no message shall go unanswered.

Home: FAQ


Home: Text
🚴‍♀️ Quick & Dirty Machine Learning with Noa Weiss

🚴‍♀️ Quick & Dirty Machine Learning with Noa Weiss

In this episode, Dean speaks with Noa Weiss, the wonderful AI & ML consultant. They dive into Deep Learning research for marine mammal sounds, abstractions for machine learning projects and some of the unspoken challenges she's seen in the ML development process. Also prediction markets and harry potter. Join our Discord community: - Timestamps: 0:00 Intro 1:24 Deep Learning research with whale sounds and how it's related to swing dancing 4:28 Why thinking about data projects as machine learning projects might be wrong 8:55 The difference between ChatGPT and GPT-3 10:41 Naive solutions in ML problems 11:24 Understanding where your company stands on the spectrum of solutions to ML problems (between an if/else statement to a sophisticated deep learning solution) 15:11 How do you think about developing ML models that will be deployed to production? 18:13 The unspoken challenges in the ML development process - surprisingly, tools aren't one of them :) 25:00 Choosing the right abstraction for your machine learning project 28:43 Noa's day-to-day – being a machine learning consultant 30:17 Machine learning in FoodTech and the Alternative Protein space 33:10 Getting started with data science in the FoodTech industry? 36:22 Predictions about the field of ML and MLOps 40:27 Rationality and whether or not predictions are useful 42:00 What do you think is true, but few people agree about ML or data science? 44:11 Recommendations for the audience Relevant Links: Noa's talks: 🎥 The Quick & Dirty AI Startup: 🎥 Choosing the Right Machine Learning Abstraction for your Business Needs – ➡️ Noa Weiss on LinkedIn – ➡️ Noa Weiss on Twitter – 🌐 Noa's website: Recommendation Links: - Unsong – - Harry Potter & The Methods of Rationality – 🌐 Check Out Our Website! Social Links: ➡️ LinkedIn: ➡️ Twitter: ➡️ Dean Pleban:
DevFest 2020  - Noa Weiss - The Unspoken Problems With Machine Learning in Security
GDG Beer Sheva

DevFest 2020 - Noa Weiss - The Unspoken Problems With Machine Learning in Security

Machine Learning is the hottest buzzword. Everybody loves it, everybody sells it. But why is it that while fields such as Computer Vision or Natural Language Processing have stellar achievements, with new record-breaking models published every other week, the Cybersecurity industry staggers behind? Are Anomaly Detection algorithms – so well beloved for the prevention of attacks and of fraud - really suitable for those intended purposes? What price do we pay for keeping things hushed? Where do our huge datasets fail us? And how, once we spot these issues, might we try and solve them? In this talk I will go over several points that hold us back, among them: our rapidly changing input data, and who’s to blame for it; the known issues of imbalanced & untagged datasets, and why our solutions for them are insufficient; and, finally, the biggest culprit: the confidential nature of our field, and how it keeps us from being great. The unspoken problems with Machine Learning in security: let’s talk about them. Language - English Noa Weiss Noa is an AI & machine learning consultant who’s been playing with data for over a decade, both in academia and in the tech industry. Prior to freelancing, Noa explored the world of risk & security, working for companies such as Armis and PayPal, as well as consulting startups on fraud prevention. In her spare time she leads the Israeli community of Women in Data Science, utilizes deep learning techniques to improve whale research at the Deep Voice foundation, and mentors junior data scientists taking their first steps in the field.
Home: Video Player


Things I've Written

Data science team management — how to do it right? A compilation.

How to classify taxonomic data like a pro.

Building your first hierarchical classification model? This post is for you.

Best practices for your hierarchical classification ensemble model.

How to measure the performance of your hierarchical classification model.

How to stay up-to-date while not losing focus on our own work.

Home: List



gfi badge solo.jpg



Facebook post logo(1).png


Community Leader



Research Engineer



Advisory Board

Home: Skills


Got an exciting new data project you want me to get on? In need of some consulting for all that machine learning? Drop me a line at:

Home: Contact
bottom of page