Paolo Giordani: SMARTboost for Tabular Data

We introduce SMARTboost (boosting of symmetric smooth additive regression trees), a machine learning model capable of fitting complex functions in high dimensions, yet designed for good performance in small n and low signal-to-noise environments. SMARTboost inherits many of the qualities that have made boosted trees the most widely used machine learning tool for tabular data; it automatically adjusts model complexity, handles continuous and discrete features, can capture nonlinear functions in high dimensions without overfitting, performs variable selection, and can handle highly non-Gaussian features. The combination of smooth symmetric trees and of carefully designed Bayesian priors gives SMARTboost an edge (in comparison with a state-of-the-art tool like XGBoost) in most settings with continuous and mixed discrete-continuous features. Unlike other tree-based methods, it can also compute marginal effects.

Image may contain: Person, Forehead, Nose, Cheek, Smile.

Paolo Giordani is professor of Financial Econometrics and former quant at BI. His main research interests are statistical machine learning, Bayesian inference, and volatility. Before joining the faculty of BI in 2018, he was a senior advisor at the research division of the Swedish Central Bank (developing statistical models and forecasting tools) and a quant in two hedge funds (developing option strategies). At BI he teaches Data Science for Finance and Quantitative Risk and Asset Management for the Msc in Quantitative Finance.

Published Mar. 2, 2022 1:02 PM - Last modified Mar. 2, 2022 2:16 PM