Feature Optimization for Time Series Forecasting via Novel Randomized Uphill Climbing

TL;DR

This paper introduces a generalized, model-agnostic feature optimization framework for multivariate time series forecasting, leveraging a stochastic search heuristic to improve interpretability and efficiency over traditional deep learning methods.

Contribution

It extends Randomized Uphill Climbing into a versatile feature discovery method that decouples from deep learning, enabling faster, more interpretable forecasting model development.

Findings

Faster iteration cycles compared to GPU-heavy models

Lower energy consumption in feature discovery process

Enhanced interpretability of forecasting features

Abstract

Randomized Uphill Climbing is a lightweight, stochastic search heuristic that has delivered state of the art equity alpha factors for quantitative hedge funds. I propose to generalize RUC into a model agnostic feature optimization framework for multivariate time series forecasting. The core idea is to synthesize candidate feature programs by randomly composing operators from a domain specific grammar, score candidates rapidly with inexpensive surrogate models on rolling windows, and filter instability via nested cross validation and information theoretic shrinkage. By decoupling feature discovery from GPU heavy deep learning, the method promises faster iteration cycles, lower energy consumption, and greater interpretability. Societal relevance: accurate, transparent forecasting tools empower resource constrained institutions, energy regulators, climate risk NGOs to make data driven decisions without proprietary black box models.