Skip to main content

Seminar by Sridhar Gollamudi

Title: From Diverse Signals to Unified Forecasts: A First-Principles Approach to Ensemble Return Prediction

Date and Time: 14 July 2025 (Monday), 11 a.m. – 12 p.m.

Venue: IEOR Seminar Room

Abstract: Performance of a quantitatively constructed portfolio critically depends on the accuracy of asset return forecasts. A widely used technique for producing strongly predictive forecasts is aggregating multiple weak forecasts from different models. In practice, these models often produce diverse outputs—ranging from forecasts on specific subsets of assets, to binary buy/sell signals, ordinal asset rankings, and even uncertainty intervals. This heterogeneity poses a significant challenge: what is a sensible way to synthesize such diverse signals into a single, cohesive forecast?
In this talk, I introduce a novel theoretical framework, derived from first principles, to ensemble heterogeneous forecasts without relying on additional assumptions about their joint distribution. The framework is complemented by efficient numerical algorithms with guaranteed convergence. I also situate this work in a broader context for the benefit of researchers beyond quantitative finance, detail its theoretical contributions, and highlight its advantages over existing heuristic methods for different types of return forecasts.

Bio: Sridhar Gollamudi is currently on garden leave from his role as Head of Risk Research at Citadel Global Quantitative Strategies, where he specialized in quantitative portfolio construction and risk modeling. Prior to Citadel, he held the same position at Two Sigma Investments. His research interests are in the general areas of buy-side quantitative finance and machine learning.

Sridhar began his career at Bell Labs, conducting research and developing products in wireless communications before transitioning into finance, a move which included a stint at Bloomberg Portfolio and Risk Analytics. He holds a B.Tech. in Electrical Engineering from IIT Bombay and a Ph.D. in Signal Processing and Communications Theory from the University of Notre Dame.