Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention

Kyle Heuton, Frederick Muench, Shikhar Shrestha, Thomas J. Stopka, Michael C Hughes
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23136-23154, 2025.

Abstract

Optimal allocation of scarce resources is a common problem for decision makers faced with choosing a limited number of locations for intervention. Spatiotemporal prediction models could make such decisions data-driven. A recent performance metric called fraction of best possible reach (BPR) measures the impact of using a model’s recommended size K subset of sites compared to the best possible top-K in hindsight. We tackle two open problems related to BPR. First, we explore how to rank all sites numerically given a probabilistic model that predicts event counts jointly across sites. Ranking via the per-site mean is suboptimal for BPR. Instead, we offer a better ranking for BPR backed by decision theory. Second, we explorehow to train a probabilistic model’s parameters to maximize BPR. Discrete selection of K sites implies all-zero parameter gradients which prevent standard gradient training. We overcome this barrier via advances in perturbed optimizers. We further suggest a training objective that combines likelihood with a BPR constraint to deliver high-quality top-K rankings as well as good forecasts for all sites. We demonstrate our approach on two where-to-intervene applications: mitigating opioid-related fatal overdoses for public health and monitoring endangered wildlife.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-heuton25a, title = {Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention}, author = {Heuton, Kyle and Muench, Frederick and Shrestha, Shikhar and Stopka, Thomas J. and Hughes, Michael C}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {23136--23154}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/heuton25a/heuton25a.pdf}, url = {https://proceedings.mlr.press/v267/heuton25a.html}, abstract = {Optimal allocation of scarce resources is a common problem for decision makers faced with choosing a limited number of locations for intervention. Spatiotemporal prediction models could make such decisions data-driven. A recent performance metric called fraction of best possible reach (BPR) measures the impact of using a model’s recommended size K subset of sites compared to the best possible top-K in hindsight. We tackle two open problems related to BPR. First, we explore how to rank all sites numerically given a probabilistic model that predicts event counts jointly across sites. Ranking via the per-site mean is suboptimal for BPR. Instead, we offer a better ranking for BPR backed by decision theory. Second, we explorehow to train a probabilistic model’s parameters to maximize BPR. Discrete selection of K sites implies all-zero parameter gradients which prevent standard gradient training. We overcome this barrier via advances in perturbed optimizers. We further suggest a training objective that combines likelihood with a BPR constraint to deliver high-quality top-K rankings as well as good forecasts for all sites. We demonstrate our approach on two where-to-intervene applications: mitigating opioid-related fatal overdoses for public health and monitoring endangered wildlife.} }
Endnote
%0 Conference Paper %T Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention %A Kyle Heuton %A Frederick Muench %A Shikhar Shrestha %A Thomas J. Stopka %A Michael C Hughes %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-heuton25a %I PMLR %P 23136--23154 %U https://proceedings.mlr.press/v267/heuton25a.html %V 267 %X Optimal allocation of scarce resources is a common problem for decision makers faced with choosing a limited number of locations for intervention. Spatiotemporal prediction models could make such decisions data-driven. A recent performance metric called fraction of best possible reach (BPR) measures the impact of using a model’s recommended size K subset of sites compared to the best possible top-K in hindsight. We tackle two open problems related to BPR. First, we explore how to rank all sites numerically given a probabilistic model that predicts event counts jointly across sites. Ranking via the per-site mean is suboptimal for BPR. Instead, we offer a better ranking for BPR backed by decision theory. Second, we explorehow to train a probabilistic model’s parameters to maximize BPR. Discrete selection of K sites implies all-zero parameter gradients which prevent standard gradient training. We overcome this barrier via advances in perturbed optimizers. We further suggest a training objective that combines likelihood with a BPR constraint to deliver high-quality top-K rankings as well as good forecasts for all sites. We demonstrate our approach on two where-to-intervene applications: mitigating opioid-related fatal overdoses for public health and monitoring endangered wildlife.
APA
Heuton, K., Muench, F., Shrestha, S., Stopka, T.J. & Hughes, M.C.. (2025). Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:23136-23154 Available from https://proceedings.mlr.press/v267/heuton25a.html.

Related Material