Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting
Machine LearningArtificial Intelligence
Summary
The authors noticed that in forecasting problems like predicting crowd sizes, it's more important to avoid underpredicting high demand than overpredicting it. They created a new training method called Asymmetric Peak-Aware Loss (APAL) that focuses more on accurately predicting demand peaks and penalizes underpredictions more heavily. They also developed special ways to measure how well models predict these peaks. Testing APAL on pedestrian count data and other benchmarks showed it improves prediction of rare spikes, though sometimes at the cost of overall average accuracy, which can be useful when peak errors are most costly.
Authors
Theivaprakasham Hari, Yanan Xin, Winnie Daamen, Serge Paul Hoogendoorn, Sascha Hoogendoorn-Lanser
Abstract
In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most time-series forecasters are trained with symmetric objectives (e.g., MSE, MAE) and evaluated primarily on aggregate error, which can mask failures in extreme-values and peak-timing predictions. We introduce Asymmetric Peak-Aware Loss (APAL), a simple, model-agnostic objective that (i) penalizes under-predictions more heavily and (ii) increases the training weight of peak regions within each forecast window. We further propose a peak-critical evaluation protocol that complements MAE/MSE with channel-wise tail error (Top-10% and Top-1%) and peak metrics (precision, recall, F1 under timing tolerance, and peak timing error). We evaluate APAL on long-horizon multivariate forecasting across five state-of-the-art backbones, with a focus on pedestrian demand forecasting using (i) a production-ready subset of the City of Melbourne pedestrian hourly count dataset and (ii) a beach visitor count dataset. The generality of the loss function for time-series forecasting is tested on additional benchmarks. Across peak-critical datasets and settings, APAL improves tail accuracy and peak-prediction quality while exposing a controllable trade-off with aggregate error, making it a practical solution when peak-prediction failures are the dominant operational concern.