Data Science & Machine Learning thought leader. Founder and Chief Data Scientist Abbott Analytics. Author of Applied Predictive Analytics (Wiley).
San Diego
Joined December 2008
- Tweets3.6K
- Following301
- Followers14.8K
- Likes987
Pinned Tweet
how about a George Box quote corollary: "no data is clean, but most is useful". #tdwiaccelerate
Competitions give you the target, data, and metric. The real world doesn’t.
The hardest part is not choosing an algorithm—it’s connecting a decision to the right analytical problem.
Video: youtube.com/watch?v=JMRcoF-h…
#DataScience #ML
How much of predictive modeling can AutoML and GenAI really handle?
On Nov. 16 in Munich, I’ll lead a full-day, hands-on masterclass at Machine Learning Week Europe—using real data and a nearly 2,500-line GenAI prompt sequence.
Details: machinelearningweek.eu/works…
#MLWEurope #GenAI
Finished my workshop on automl + GenAI at #MLWeek last week. I'm loving being able to introduce ideas into prompts for Claude and/or ChatGPT to do things I love doing but rarely see and get code to execute (it wrote over 6000 lines of code for me to use in demos...I created these within a few hours). One example is using ISLE (minitab.com/content/dam/www/…) which compresses GBM ensembles: reducing # of trees and tends to be more accurate on hold-out data. Prompt->code->run it.
Appreciate the insights on why LLMs struggle with breaking news.
I wonder how many humans are employed to fix them? This is why I recommend to those who ask me to not use LLMs open loop for mission critical tasks without human validation.
open.substack.com/pub/garyma…
Dean Abbott retweeted
🧠 Predictive or generative AI? Why not both.
Join Dean Abbott at #MLWeek for a session on hybrid AI for retail fraud detection.
📅 June 3 | ⏰ 10:30 AM
🔗machinelearningweek.com/sess…
#machinelearning @deanabb
Dean Abbott retweeted
Read my latest in @Forbes: When #machinelearning fails to detect misinformation, medical conditions or spam, the cost of each error is subjective. Here’s how to apply #predictiveAI nonetheless. forbes.com/sites/ericsiegel/…
Dean Abbott retweeted
Read my latest @Forbes article. Stakeholders involved with #predictiveAI must ramp up on a semi-technical understanding that comes down to 1) what's predicted, 2) how well, and 3) what's done about it. forbes.com/sites/ericsiegel/… #bizML
I'll be back at Machine Learning Week, EU, this year in Munich! Changing my workshop to an AutoML/Predictive AI/Generative AI topic this time.
Hope to see many of you there!
#MachineLearning #AI #Workshop #MachineLearningWeekEU #PredictiveAnalytics
Dean Abbott retweeted
👇 Devastating new paper. The lack of reliable world models will forever hobble LLMs (exactly as I conjectured in 2019).
Can language models be used as world simulators? In our ACL 2024 paper, we show -- not really.
GPT-4 is only ~60% accurate at simulating state changes based on common-sense tasks, like boiling water.
Preprint: arxiv.org/pdf/2406.06485
@allen_ai @MSFTResearch @aclmeeting
So glad you found it so helpful! Thanks for your comments and questions during the workshop.
Had an incredible time at @MLWeekUS ! The session on predictive and generative AI by @deanabb were truly insightful. Excited to apply what I've learned and see where this cutting-edge tech takes us next! #MLWeek #AI #MachineLearning
Onsite edition of #SanDiego #KNIME Data Connect will take place on Jan 9, 2024 at Extended Studies Center 5701 Hardy Ave San Diego, CA, 5PM onwards.
This event will showcase real world examples from practising marketing data scientists and Analyzing the customer journey from end to end using KNIME.
This is intended to be a monthly meetup, some in-person and some virtual.
meetup.com/san-diego-knime-u…
#MachineLearning #DataScience #MarketingAutomation
Dean Abbott retweeted
I will be presenting this webinar on AI in financial services & fintech. Nearly a full house. But it's not too late, join us!
#AI #DigitalTransformation #Compliance
@bornonjuly4 @dmgerbino @rwang0 @jenstirrup @data_nerd @predictanalytic @KirkDBorne @deanabb @schmarzo
Join us on October 12 for a complimentary BAI webinar on AI. We will cover many of the key questions financial services organizations have along with what resources are available to help them create AI policies to help safeguard company information. bit.ly/46xNPjN
Dean Abbott retweeted
Announcing my second book, "The AI Playbook: Mastering the Rare Art of Machine Learning Deployment"! Pre-order with this link by Friday for a @BNBuzz special (25% off for standard rewards members and 10% for premium members). Special thanks to @mitpress. barnesandnoble.com/w/the-ai-…
Very much enjoyed my conversation with Ryan Atkinson of the TechGuide. While the topic is "starting" a career in data analytics, and data science in particular, there are also several topics discussed that are not necessarily "intro" topics, such as how t…lnkd.in/gqrtNdue
I’m happy to share that I’m starting a new position as Bodily Bicentennial Professor of Analytics at University of Virginia Darden School of Business! #analytics lnkd.in/gS_BzTGM
Start of talk by William Komp on Data Science solutions inspired by physics. No one better qualified for this talk! lnkd.in/gy2iKVUU
Is AI hyped? We all know it is. But is there a tangible downside to the hype? @predictanalytic explains what the downside for machine learning as it rides in the wake of AI. #machinelearning #ai #predictiveanalytics lnkd.in/g7gab4Jx
Quick intro for my talk at this year's Machine Learning Week (@mlweekus), abstract here: predictiveanalyticsworld.com…
Model Selection Using the Right Error Metric: The “Best” Model May Not Be Good youtu.be/4kDV4GOP2AQ via @YouTube