LLMs for Equities Feature Forecasting at Two Sigma [Ben Wellington] - 736

Today, we're joined by Ben Wellington, deputy head of feature forecasting at Two Sigma. We dig into the team’s end-to-end approach to leveraging AI in equities feature forecasting, covering how they identify and create features, collect and quantify historical data, and build predictive models to forecast market behavior and asset prices for trading and investment. We explore the firm's platform-centric approach to managing an extensive portfolio of features and models, the impact of multimodal LLMs on accelerating the process of extracting novel features, the importance of strict data timestamping to prevent temporal leakage, and the way they consider build vs. buy decisions in a rapidly evolving landscape. Lastly, Ben also shares insights on leveraging open-source models and the future of agentic AI in quantitative finance. 🗒️ For the full list of resources for this episode, visit the show notes page: https://twimlai.com/go/736. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confirmation=1 🗣️ CONNECT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Follow us on Twitter: https://twitter.com/twimlai Follow us on LinkedIn: https://www.linkedin.com/company/twimlai/ Join our Slack Community: https://twimlai.com/community/ Subscribe to our newsletter: https://twimlai.com/newsletter/ Want to get in touch? Send us a message: https://twimlai.com/contact/ 📖 CHAPTERS =============================== 00:00 - Introduction 3:18 - Feature forecasting at Two Sigma 6:31 - Feature forecaster’s workflow 9:33 - Importance of recording data 13:13 - Raw data vs. derivative features 17:06 - Features 20:13 - Feature extraction in the GenAI era 24:19 - Embedding evolution 25:15 - Use cases 29:21 - Two Sigma platform 32:49 - Predictions and portfolio optimization 36:02 - Future of agentic models 38:29 - Build vs. buy 40:50 - Weighing investment decisions 42:23 - AutoML 43:59 - Modular vs. end-to-end 46:44 - Interpretability 48:52 - Open source models 51:11 - Combinatorial research 55:08 - Safety measures on data leakage 57:07 - Future predictions 🔗 LINKS & RESOURCES =============================== Two Sigma - https://www.twosigma.com/ Waymo’s Foundation Model for Autonomous Driving with Drago Anguelov - 725 - https://twimlai.com/podcast/twimlai/waymos-foundation-model-for-autonomous-driving/ Building AI Voice Agents with Scott Stephenson - 707 - https://twimlai.com/podcast/twimlai/building-ai-voice-agents/ Web Scale Engineering for Machine Learning with Sharath Rao - 40 - https://twimlai.com/podcast/twimlai/web-scale-engineering-machine-learning-sharath-rao/ 📸 Camera: https://amzn.to/3TQ3zsg 🎙️Microphone: https://amzn.to/3t5zXeV 🚦Lights: https://amzn.to/3TQlX49 🎛️ Audio Interface: https://amzn.to/3TVFAIq 🎚️ Stream Deck: https://amzn.to/3zzm7F5