@inproceedings{10.1145/3744916.3764539,
author = {Puccinelli, Niccol{\`o} and Molinelli, Davide and El Moussa, Noura and Ciniselli, Matteo and Pezz{\`e}, Mauro},
title = {Predicting Failures in Smart Human-Centric Ecosystems},
year = {2026},
isbn = {9798400720253},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3744916.3764539},
doi = {10.1145/3744916.3764539},
abstract = {Smart cities, smart grids, and in general Smart Human-centric Ecosystems (SHEs) emerge from the co-existence of many systems that operate according to independently owned specifications, and evolve over time. SHEs may fail despite the correct behavior of the systems that comprise the SHEs. Fully testing SHEs on testbeds to prevent failures in production is impossible, and scenarios that may lead to catastrophic SHE failures are unavoidable.In this paper we frame the core issues of SHE failures, and propose Smart human-centric Ecosystem Monitoring, SEM, an approach that predicts SHE failures to enable corrective actions for mitigating the catastrophic effects of failures. SEM identifies failure-prone scenarios from the reconstruction error of SHE indicators, that is, metric values that SEM collects from the SHE at constant frequency. SEM computes the reconstruction error with a suitably trained denoising autoencoder combined with a transformer architecture. The results of experimenting with a peer-to-peer ride-hailing ecosystem operating in San Francisco confirm that SEM can effectively predict SHE failures early enough to activate preventing actions, and indicate the generalizability of SEM with continual learning.The main contributions of the paper are the definition and the exemplification of the impact of failures in SHEs, and an approach to detect incoming failures before otherwise inevitable disruptive effects.},
booktitle = {Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering},
pages = {3285–3297},
numpages = {13},
keywords = {Smart Human-centric Ecosystems, Failure Prediction, Autoencoders},
location = {
},
series = {ICSE '26}
}