# Overlaydx - Automating forecasting evaluation

arXiv: https://arxiv.org/abs/2609.24586 · HTML: https://mlsanity.com/paper/2609.24586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 25 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 2 of 2)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Mean Absolute Percentage Error for regression models](https://mlsanity.com/paper/1605.02541/) (2016)

## Abstract (arXiv)

Traditional evaluation metrics provides numerical values but often lack comprehensibility, hindering effective differentiation of model performances. Our work addresses this challenge by introducing overlaydx, a novel evaluation metric measuring the performance of time series prediction models. Overlaydx is a visual metric that represents the percentage of predictions falling within a confidence interval around actual values. Additionally, once evaluation results are plotted, overlaydx computes the area under the overlay curve, providing a quantitative measure of alignment between predicted and actual values across different thresholds and predictions. Through extensive experiments, we demonstrate that our approach offers a unified evaluation framework that combines both visual and numerical assessments, enabling improved model comparison and providing valuable insights for further research and optimization efforts in time series prediction.