Kumo unveils world's first Relational Foundation Model (RFM) for instant predictions on enterprise data
MOUNTAIN VIEW, Calif., May 20, 2025 /PRNewswire/ -- Kumo, a leader in predictive AI, announced today the launch of KumoRFM, which allows businesses to instantly generate accurate predictions, such as item recommendations, identifying customer churn, or detecting fraudulent transactions, directly from their enterprise data. The first-ever foundation model built for relational data, KumoRFM gives organizations of any size an off-the-shelf, cost-effective AI model that eliminates the need to manually build and train separate models for each predictive task. KumoRFM results in 20x faster time to value and delivers 30-50% higher accuracy compared to traditional approaches.
AI has completely transformed how businesses leverage text-based and unstructured data like documents, audio, video, and images. Yet, structured enterprise data — like customer records, transaction histories, and product catalogs — is the backbone of business decision-making, but remains largely untouched by this wave of AI innovation.
"To make predictions and business decisions, even the largest and most cutting-edge companies are using 20-year-old machine learning techniques on the enterprise data inside their data warehouses," said Jure Leskovec, Co-Founder and Chief Scientist at Kumo. "Extending Transformer architecture beyond natural language took significant innovation and investment. We're proud to bring to enterprise data what GPTs brought to text, and at a fraction of the cost."
KumoRFM is the first model to deliver instant predictions on structured enterprise data, without the need for task-specific model training. While language models such as ChatGPT use their understanding of semantic meaning within text to generate the next word, KumoRFM uses its understanding of traits, behaviors, and relationships represented inside data warehouses to predict what business outcomes will be at a different time or in a different scenario. These predictions power critical business decisions, from flagging suspicious transactions to recommending products, personalizing marketing offers, and selecting which ads or content to display. All of which have a direct impact on revenue.
Data science teams, developers, and engineers can connect KumoRFM to their data warehouse through an API, and KumoRFM can begin immediately identifying patterns within the enterprise's data and make business-critical predictions, like customer churn, personalized customer recommendations, and fraud detection. Unlike traditional approaches that require building and training separate models for each such predictive task, KumoRFM is zero-shot, enabling accurate predictions without the need to even train or specialize the model. This shift allows AI and engineering teams to get predictions for different use cases in real-time, letting them explore and ship applications faster. KumoRFM is trained solely on synthetic enterprise-like data, which makes the model compact and inference cost-effective.
"AI tools like chatbots and content generators have shown what's possible with language, but there's a missing piece when it comes to enterprise data, and KumoRFM fills that gap," said Vanja Josifovski, Co-Founder and CEO at Kumo. "The game changes completely when AI connects with business data. That's when we see the needle move. Real numbers, real ROI, and real business impact."
KumoRFM is a pre-trained Relational Graph Transformer model, enabling it to learn across multiple tables of structured enterprise data. KumoRFM works out of the box, delivering instant predictions with accuracy on par with manual models. When fine-tuned to a specific task, KumoRFM delivers 30-50% higher accuracy compared to traditional approaches. The model is built on years of research in Graph Neural Networks (GNNs) and Graph Transformers, a field pioneered by Jure Leskovec and several members of the Kumo team. This core technology, available through an API, already powers Kumo's existing platform, which is used by more than 20 enterprise clients, including DoorDash, Databricks, Snowflake, and Reddit. To get started, visit Kumo.AI.
Follow Kumo
LinkedIn: https://www.linkedin.com/company/kumo-ai/X (formerly Twitter): https://twitter.com/Kumo_ai_teamKumo Research: https://kumo.ai/research/
About Kumo
Kumo transforms how businesses create predictions from their data warehouse, using AI to quickly build high-performing machine learning models that help data scientists better predict user and customer behaviors with best-in-class accuracy. The company was founded by three PhDs who have held executive leadership and academic positions at Pinterest, Airbnb, LinkedIn, and Stanford. Kumo has raised $37 million in funding and is backed by Sequoia Capital. Kumo is reshaping the future of applications, making predictive AI accessible and practical for companies of all sizes. To learn more, visit kumo.ai.
Contact:
Ali GoldbergConcrete Media for Kumokumo@concrete.media
View original content to download multimedia:https://www.prnewswire.com/news-releases/kumo-unveils-worlds-first-relational-foundation-model-rfm-for-instant-predictions-on-enterprise-data-302460899.html
SOURCE Kumo.AI
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
3 hours ago
- Yahoo
CGTN: How China's economy remains vibrant despite U.S. tariff war
BEIJING, July 25, 2025 /PRNewswire/ -- With Chinese Vice Premier He Lifeng to hold economic and trade talks with the United States in Sweden later this month, the strength and resilience of the Chinese economy is in the limelight once again. This round of talks, mutually agreed upon by both nations, is not only a diplomatic engagement but also a testament to China's enduring economic vitality in a complex international environment. Recent statistics underscore the robustness of China's economy. In the first half of 2025, the GDP grew by an impressive 5.3 percent year on year, surpassing market expectations despite global headwinds. This number reflects more than temporary growth; it exhibits the structural resilience and adaptability of an economy that continues to evolve and upgrade. Domestic demand emerged as the cornerstone of growth, contributing 68.8 percent to GDP expansion in this period. Initiatives such as large-scale equipment upgrades and consumer goods trade-in programs have effectively stimulated spending, cushioning China's economy from external shocks. In the first five months of 2025 alone, China's consumer goods trade-in program generated 1.1 trillion yuan ($153.1 billion) in sales, surpassing the figure for entire 2024. Boosted by the program, China's retail sales of consumer goods grew 5 percent year on year in the past six months – 0.4 percentage point faster than the growth recorded in the first quarter. While external uncertainties have introduced some pressure, China's trade diversification and the steady output of high-tech manufacturing and service industries have provided strong support to the economy. Though China's trade with some Western countries declined, its trade with Belt and Road partners, ASEAN countries, the European Union, and African nations saw respective increases of 4.7 percent, 9.6 percent, 3.5 percent, and 14.4 percent in the first half of 2025. This expansion of trade relationships has helped China reduce its reliance on any one market, lessening the impact of some Western economies' protectionist policies. China's resilience reverberates beyond its borders. As a crucial driver of global growth, China's steady economic performance boosts international market confidence and provides a stabilizing influence amid global uncertainties. Through continued focus on quality growth and opening up, China offers the international community a reliable engine for shared prosperity. A recent report from the U.S.-China Business Council indicates that 82 percent of American companies operating in China turned a profit in 2024. Though many cited the uncertainties in China-U.S. relations and tariffs as their main worry, the Chinese market continues to be crucial for them. Trade tensions pose obstacles, yet they have not crippled the resilience in the Chinese economy. The upcoming Beijing-Washington talks in Sweden demonstrate China's willingness to tackle differences via negotiations. While obstacles remain, China's ability to sustain growth, adapt to changing global landscapes, and engage constructively with international partners signals a future of shared opportunities and mutual advancement. View original content to download multimedia: SOURCE CGTN
Yahoo
3 hours ago
- Yahoo
Here's ChatGPT's advice on how to spot the next meme stock
Amid this week's speculative euphoria, we asked ChatGPT what makes a meme stock. The chatbot laid out four things for investors to focus on. The AI also had some ideas about what stocks might be next in line for a short squeeze. What makes a meme stock? ChatGPT has a couple of ideas. When shares of Opendoor Technologies, a little-known online real estate platform, unexpectedly started surging this month, a few other seemingly random names followed. The list of stocks included Krispy Kreme, Kohl's, and GoPro, disparate companies united only by their financial challenges and vaguely retro vibes. On the surface, meme stocks that go parabolic have little in common, but if you look under the hood, there are some similarities in their profiles. How to find the next meme stock? We asked ChatGPT Since the GameStop short squeeze of 2021, investors have been trying to spot the next meme stock before it starts its ascent to the moon. After seeing some investors bragging on Wall Street Bets about getting winning trading advice from ChatGPT, we decided to test the AI's knowledge of the market's speculative frenzy. (We will preface all of this by saying it's not real investment advice. ChatGPT is scouring the internet—including Wall Street Bets! — for wisdom on the subject.) The prompt was: "What's the best way to identify what could be the next meme stock?" After clarifying what a meme stock is, the chatbot responded that identifying one is "more of an art than a science." It then proceeded to lay out some more detailed criteria for investors to think about: High short interest (>20% float), Days-to-cover ≥5The bot suggested Kohl's, Opendoor, and GoPro as examples of stocks with high interest from short sellers, naming and ShortInterestTracker as tools for assessment. Surge in social mentions (Reddit/Twitter)It highlighted the importance of noting sudden increases in a sock's mentions or upvotes on social media platforms such as X, Reddit and Discord, citing platforms including ApeWisdom and AltIndex. Unusual options activity (OI spikes)While discussing unusual options activity, it stated that "retail traders often pile into out-of-the-money (OTM) call options, creating gamma squeezes as market makers hedge by buying shares-fueling price surges." Meme narrative (pop‑culture, underdog story)ChatGPT highlighted the importance of a narrative, citing the David vs. Goliath mentality that drove the GameStop short squeeze or companies with products popular with retail investors, such as Krispy Kreme or AMC Entertainment, a fellow struggling meme stock. Wanting to test the AI's predictive abilities, we asked: "Based on this criteria, can you predict the next meme stock?" ChatGPT quickly named American Eagle Outfitters as its pick for the next meme stock based on its criteria, providing reasons it checks all four boxes. Per the bot: Social Media MomentumIts recent ad campaign starring Sydney Sweeney has ignited buzz across Reddit, X, and Stocktwits, pushing the stock up ~10% on the Interest & Squeeze PotentialWith ~13% of its float shorted, there's room for a squeeze if sentiment continues to climb. Options FlowEarly reports suggest call option volume has ticked upward around recent campaign news. Narrative + Meme-WorthinessThe Sydney Sweeney campaign taps into pop-culture, star power, and a viral storyline — all classic ingredients for meme stock fervor." Indeed, the fashion retailer's new ad campaign featuring Sweeney has made American Eagle a top trending stock across retail trading forums. While the stock is only up 11% for the week, the assessment shows that ChatGPT can spot trends as they're unfolding. Though it wasn't asked to, the chatbot added honorable mentions to what could be the next meme stock, including Krispy Kreme, GoPro, and Rocket Lab USA. It should be noted that these aren't great picks by the bot, as all of these stocks were already fading after surging earlier in the week. Meanwhile, RocketLab, though it has fairly high short interest, is not actually a meme stock. It is possible that ChatGPT confused it with Rocket Companies, which has much higher short interest and was among the meme shares to surge this the original article on Business Insider Sign in to access your portfolio
Business Insider
3 hours ago
- Business Insider
Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI
Shengjia Zhao, a co-creator of ChatGPT and former lead scientist at OpenAI, is joining Meta as chief scientist of its Superintelligence Labs. CEO Mark Zuckerberg announced Zhao's appointment on Friday in a social media post, and called him a "pioneer" in the field who has already driven several major AI breakthroughs. Zhao previously helped build GPT-4 and led synthetic data efforts at OpenAI. According to the post, Zhao will now work directly with Zuckerberg and Meta's newly appointed chief AI officer, Alexandr Wang, the founder and CEO of Scale AI. The new hire comes during Zuckerberg's multibillion-dollar AI spending spree, including a $15 billion investment in Scale AI and the creation of Meta Superintelligence Labs, a new division focused on foundational models and next-gen research. In addition to Zhao, the company has lured away the three researchers who built OpenAI's Zurich office — Lucas Beyer, Alexander Kolesnikov, and Xiaohua Zhai — all of whom previously also worked at Google's DeepMind. The Superintelligence Labs team is now comprised of a lineup of names previously seen with OpenAI, Anthropic, and Google. But the war for AI talent is far from over. Databricks VP Naveen Rao likened the competition to "looking for LeBron James," estimating that fewer than 1,000 people worldwide can build frontier AI models. Companies without the cash for massive pay packages are turning to hackathons and computing power as incentives. Perplexity CEO Aravind Srinivas said a Meta researcher he tried to poach told him to ask again when the company has "10,000 H100s." AI tech workers have previously told Business Insider that Meta's Mark Zuckerberg has been emailing prospects directly and even hosting AI researchers at his home, while OpenAI CEO Sam Altman has made personal calls to potential hires. Tech company executives have mixed feelings about Meta's poaching efforts. "Meta right now are not at the frontier, maybe they'll they'll manage to get back on there," said Demis Hassabis, the CEO of Google DeepMind, on an episode of the "Lex Fridman Podcast," which aired on Friday. "It's probably rational what they're doing from their perspective because they're behind and they need to do something," Hassabis added. During a July 18 episode of the podcast "Uncapped with Jack Altman," OpenAI CEO Sam Altman criticised some of Meta's "giant offers" to his company's employees, and called the strategy "crazy."
