# SCOPE: Sequential Causal Optimization of Process Interventions

arXiv: https://arxiv.org/abs/2512.17629 · HTML: https://mlsanity.com/paper/2512.17629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 18 of 18)

- [Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms](https://mlsanity.com/paper/2101.10943/) (2021)
- [Survey and cross-benchmark comparison of remaining time prediction methods in business process monitoring](https://mlsanity.com/paper/1805.02896/) (2018)
- [Prescriptive Business Process Monitoring for Recommending Next Best Actions](https://mlsanity.com/paper/2008.08693/) (2020)
- [Prescriptive Process Monitoring for Cost-Aware Cycle Time Reduction](https://mlsanity.com/paper/2105.07111/) (2021)
- [Alarm-Based Prescriptive Process Monitoring](https://mlsanity.com/paper/1803.08706/) (2018)
- [Prescriptive Process Monitoring: Quo Vadis?](https://mlsanity.com/paper/2112.01769/) (2021)
- [Prescriptive Process Monitoring Under Resource Constraints: A Causal Inference Approach](https://mlsanity.com/paper/2109.02894/) (2021)
- [Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects](https://mlsanity.com/paper/2205.14714/) (2022)
- [IGC-Net for conditional average potential outcome estimation over time](https://mlsanity.com/paper/2405.21012/) (2024)
- [Learning When to Treat Business Processes: Prescriptive Process Monitoring with Causal Inference and Reinforcement Learning](https://mlsanity.com/paper/2303.03572/) (2023)
- [Intervening With Confidence: Conformal Prescriptive Monitoring of Business Processes](https://mlsanity.com/paper/2212.03710/) (2022)
- [Learning optimal policies from event logs through reinforcement learning: a comparison of deep and MDP-based approaches](https://mlsanity.com/paper/2303.09209/) (2023)
- [Prescriptive Process Monitoring Under Resource Constraints: A Reinforcement Learning Approach](https://mlsanity.com/paper/2307.06564/) (2023)
- [Optimizing Treatment Allocation in the Presence of Interference](https://mlsanity.com/paper/2410.00075/) (2024)
- [SimBank: from Simulation to Solution in Prescriptive Process Monitoring](https://mlsanity.com/paper/2506.14772/) (2025)
- [Bridging the Reality Gap in Digital Twins with Context-Aware, Physics-Guided Deep Learning](https://mlsanity.com/paper/2505.11847/) (2025)
- [Identifying optimally cost-effective dynamic treatment regimes with a Q-learning approach](https://mlsanity.com/paper/2107.03441/) (2021)
- [An Innovative Data-Driven and Adaptive Reinforcement Learning Approach for Context-Aware Prescriptive Process Monitoring](https://mlsanity.com/paper/2501.10543/) (2025)

## Abstract (arXiv)

Prescriptive Process Monitoring (PresPM) recommends interventions during running business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of interventions to jointly steer the outcome of a case. Existing PresPM approaches only partially address this challenge. Many focus on a single intervention decision, while others treat multiple interventions independently, ignoring how they interact over time. Methods that do address these dependencies depend either on simulation or data augmentation to approximate the process to train a Reinforcement Learning (RL) agent, which may create a reality gap and introduce bias. We introduce SCOPE (Sequential Causal Optimization of Process Interventions), a PresPM approach that learns aligned sequential intervention recommendations. SCOPE employs backward induction to estimate the effect of each candidate intervention action, propagating its impact from the final decision point back to the first. By leveraging causal learners, our method can utilize observational data directly, unlike methods that require constructing process approximations for RL. Experiments on both an existing synthetic dataset and a new semi-synthetic dataset show that SCOPE consistently outperforms state-of-the-art PresPM techniques in optimizing the KPI. The novel semi-synthetic setup, based on a real-life event log, is provided as a reusable benchmark for future work on sequential PresPM.