Actor-Enriched Time Series Forecasting of Process Performance

TL;DR

The paper tackles forecasting daily throughput time $\mathcal{TT}$ in predictive process monitoring by incorporating actor behavior as time-varying features. It introduces a framework that constructs baseline TT features and actor-enriched features, then models the target via $\Delta \mathcal{TT}$ residuals and reconstructs TT. Experiments on three BPIC datasets show actor-enriched models consistently outperform TT-only baselines across ARIMA, XGBoost, LightGBM, and RNN variants, with tree-based models yielding the largest gains. These results highlight the practical value of dynamic resource-aware signals for process performance forecasting and motivate further work on richer actor representations.

Abstract

Predictive Process Monitoring (PPM) is a key task in Process Mining that aims to predict future behavior, outcomes, or performance indicators. Accurate prediction of the latter is critical for proactive decision-making. Given that processes are often resource-driven, understanding and incorporating actor behavior in forecasting is crucial. Although existing research has incorporated aspects of actor behavior, its role as a time-varying signal in PPM remains limited. This study investigates whether incorporating actor behavior information, modeled as time series, can improve the predictive performance of throughput time (TT) forecasting models. Using real-life event logs, we construct multivariate time series that include TT alongside actor-centric features, i.e., actor involvement, the frequency of continuation, interruption, and handover behaviors, and the duration of these behaviors. We train and compare several models to study the benefits of adding actor behavior. The results show that actor-enriched models consistently outperform baseline models, which only include TT features, in terms of RMSE, MAE, and R2. These findings demonstrate that modeling actor behavior over time and incorporating this information into forecasting models enhances performance indicator predictions.

Figures (3)

• Figure 1: Overview of the methodology for incorporating actor behavior into TT prediction.
• Figure 2: Illustration of reconstructing the target variable TT by incrementally adding predicted smoothed $\Delta TT$ values to a base value.
• Figure 3: Top 10 most important predictive features (by mean SHAP value) for actor-enriched XGBoost and LightGBM models across all datasets.