Human in the Loop Adaptive Optimization for Improved Time Series Forecasting

TL;DR

This paper presents a lightweight, model-agnostic framework that enhances time series forecasting accuracy through adaptive corrections optimized via reinforcement learning or genetic algorithms, with optional human guidance.

Contribution

It introduces a novel post-training adaptive optimization method that improves forecasts without retraining or changing model architecture, incorporating human-in-the-loop capabilities.

Findings

Consistent accuracy improvements across multiple benchmarks.

Affine corrections always reduce mean squared error.

Framework operates with minimal computational overhead.

Abstract

Time series forecasting models often produce systematic, predictable errors even in critical domains such as energy, finance, and healthcare. We introduce a novel post training adaptive optimization framework that improves forecast accuracy without retraining or architectural changes. Our method automatically applies expressive transformations optimized via reinforcement learning, contextual bandits, or genetic algorithms to correct model outputs in a lightweight and model agnostic way. Theoretically, we prove that affine corrections always reduce the mean squared error; practically, we extend this idea with dynamic action based optimization. The framework also supports an optional human in the loop component: domain experts can guide corrections using natural language, which is parsed into actions by a language model. Across multiple benchmarks (e.g., electricity, weather, traffic), we observe consistent accuracy gains with minimal computational overhead. Our interactive demo shows the framework's real time usability. By combining automated post hoc refinement with interpretable and extensible mechanisms, our approach offers a powerful new direction for practical forecasting systems.