Shubhranshu Shekhar

Assistant Professor @BrandeisBiz @BrandeisU. PhD @CarnegieMellon. Anomaly Detection. Data Mining. Social Impact.

[Shubhranshu Shekhar @dahi_chuda]

@marthagimbel It'd be interesting to see how budget lab's model and a small foundational macro model compare. https://t.co/6Pksi7AoyU

[Econometrics Papers @eBlogs]

MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting

Andrea Carriero, Davide Pettenuzzo, Shubhranshu Shekhar
https://t.co/LG6fNfFCoy [𝚎𝚌𝚘𝚗.𝙴𝙼 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

[Shubhranshu Shekhar @dahi_chuda]

Links to resources.
📄 Paper: https://t.co/7Qhc4PyFxt

💻 GitHub:
https://t.co/M5yeKWZWTK

🤗 Hugging Face:
https://t.co/2IW7t0Gj1P

📓 Google Colab:
https://t.co/mlcvxYBUtm

I'd love to hear your thoughts and feedback!

#MachineLearning #TimeSeries #Forecasting

[Shubhranshu Shekhar @dahi_chuda]

1/6

🚀 Excited to share MacroCast: a vintage-consistent Time Series Foundation Model for real-time macroeconomic forecasting.

The biggest challenge with applying TSFMs to macro data is data leakage. MacroCast is the first TSFM designed to eliminate it entirely.

[Shubhranshu Shekhar @dahi_chuda]

Despite being lightweight:

⚡ ~1M parameters
⚡ ~9 minutes to retrain per vintage
📈 Matches or outperforms leading TSFMs and econometric models on the full FRED-MD benchmark in a genuine real-time evaluation.

[Shubhranshu Shekhar @dahi_chuda]

@BenjaminShiller A bit tangential: Is the student learning better or are they just experiencing lower cognitive friction coz reviewing? May be worth doing an experiment.

[Shubhranshu Shekhar @dahi_chuda]

Paper: https://t.co/P4yAVzSNE7
Economic Report: https://t.co/GXTyrqRjhA

[Shubhranshu Shekhar @dahi_chuda]

A personal weekend highlight! Just found out our paper on ML fraud detection was cited in the 2025 U.S. Joint Economic Report. Our research showing up in Congressional policy docs is wild (and super cool). Feeling pretty great about this one! ✨✨
Paper 👇👇

[Shubhranshu Shekhar @dahi_chuda]

@davidabann @ryancbriggs Super cool. Thanks for sharing.

[Shubhranshu Shekhar @dahi_chuda]

@ryancbriggs Thank you! Watching this space for the repo.

[Journal of Policy Analysis and Management @JPAM_DC]

Recently published at JPAM: "Can Machine Learning Target Health Care Fraud? Evidence From Medicare Hospitalizations" by Shubhranshu Shekhar, Jetson Leder-Luis, & Leman Akoglu.
https://t.co/WZxZBTf5uo

[Shubhranshu Shekhar @dahi_chuda]

@emaadmanzoor On a different note, I recognize that F17 project.

[Juri Marcucci @JuriMarcucci]

1/
📢 This Friday!
Join us for the next #AMLEDS #webinar featuring @TaraSinc (GWU) presenting her #FOMC In Silico" paper with @SophiaKazinnik (@Stanford).
🕚 11AM ET-5PM CET
💻 Zoom
📄 Paper → https://t.co/TXV4N68M3k
#EconTwitter #AI #LLMs #NLP

[Nicholas Fabiano, MD @NTFabiano]

You're not depressed, you just lost your quest.

[Shubhranshu Shekhar @dahi_chuda]

@ramkris Super congratulations!!

[Shubhranshu Shekhar @dahi_chuda]

Navigating AI adoption & governance? 🤖 We're researching how orgs are tackling this challenge. If you influence AI decisions, we need your insights to shape industry standards.

Take our quick (5-7 min) confidential survey: https://t.co/kt9ELLy9oR

#AIGovernance #EnterpriseAI

[Peyman Milanfar @docmilanfar]

You should be so lucky to have people throughout your research career that you can openly bounce ideas to and from - especially if they complement your strengths in your areas of weakness - it is a rare and precious gift.