Neural networks have become a popular tool in predictive modelling, more commonly associated with machine learning and artificial intelligence than with statistics. Generalised Additive Models (GAMs) are flexible non-linear statistical models that retain interpretability. Both are state-of-the-art in their own right, with their respective advantages and disadvantages. This paper analyses how these two model classes have performed on real-world tabular data. Following PRISMA guidelines, we conducted a systematic review of papers that performed empirical comparisons of GAMs and neural networks. Eligible papers were identified, yielding 143 papers, with 430 datasets. Key attributes at both paper and dataset levels were extracted and reported. Beyond summarising comparisons, we analyse reported performance metrics using mixed-effects modelling to investigate potential characteristics that can explain and quantify observed differences, including application area, study year, sample size, number of predictors, and neural network complexity. Across datasets, no consistent evidence of superiority was found for either GAMs or neural networks when considering the most frequently reported metrics (RMSE, R 2 , and AUC). Neural networks tended to outperform in larger datasets and in those with more predictors, but this advantage narrowed over time. Conversely, GAMs remained competitive, particularly in smaller data settings, while retaining interpretability. Reporting of dataset characteristics and neural network complexity was incomplete in much of the literature, limiting transparency and reproducibility. This review highlights that GAMs and neural networks should be viewed as complementary approaches rather than competitors. For many tabular applications, the performance trade-off is modest, and interpretability may favour GAMs.

Abstract Process task duration data often exhibit multiple peaks, indicating differences in, for example, customer ages and preferences, resource capabilities or the day/hour of a week. This heterogeneous data, which captures diverse customer patterns, should be represented using different models, resulting in an overall mixture model. This paper introduces gamma mixture models to represent various customer patterns in task duration data, with a focus on automating the fitting process. The approach involves a two-stage procedure: first, divide-and-conquer using peak-, equidistance- and cluster-based techniques to partition data, and automatically fit gamma distributions to each subset. The second stage then improves the fitted mixture model by directly searching the log-likelihood surface. The method is compared with the expectation–maximization (EM) algorithm and an open tool (HyperStar), using both artificially generated datasets and a publicly available hospital billing dataset, demonstrating its effectiveness and time efficiency in modelling heterogeneous process duration data. Furthermore, a case study on process conformance checking is conducted using the hospital billing dataset, highlighting a potential application area for the method in process mining.

Within the realm of business context, process duration signifies time spent by customers between successive activities. This temporal perspective offers important insight to customer behavior, highlighting potential bottlenecks, and influencing business management decisions. The distribution of these process duration often changes over time due to factors such as seasonality, emerging legislation, changes to supply chains, and customer demand. Referred to as concept drift, these variations pose challenges for robust process modeling, understanding, and refinement. Subsequently, gamma mixture models are widely employed to model durations. These source data can, however, become left-truncated and right-censored within any specific observation window thereby necessitating a (well-known) modification to the likelihood function. The approach reported in this article leveraged this adapted likelihood across a series of observation windows, applying the likelihood ratio test to identify duration changes/concept drift. Due to its flexibility in modelling any duration distribution, the gamma mixture model was used with Nelder–Mead optimized likelihood for the left-truncated and right-censored data. The number of gamma components was determined by the Bayesian information criterion. The proposed framework underwent validation through simulated exponential samples, leading to recommendations for its practical application. Subsequently, we applied the methodology to three real-life event logs exhibiting diverse characteristics. Experimental results showcase the effectiveness of our approach in terms of data fitting, as compared to Kaplan–Meier curves, and in detecting instances of drift. This comprehensive validation underscores the practical utility and reliability of our framework for dynamic business scenarios.

The motivation for this work comes from the tension that students experience when considering participating in co-curriculars and meeting their curricular obligations. There is evidence highlighting a range of benefits from student involvement in co-curricular experiences, including cognitive gains, development of professional competencies, and sense of belonging. Despite these benefits, many undergraduate students have little or no co-curricular involvement. This research seeks to better understand how engineering undergraduates balance their time and navigate educational opportunities. Using the National Survey of Student Engagement (NSSE) as a guide, we implemented a daily time-tracking survey and piloted it in a first-year engineering course. The survey included 14 items to capture data on how students spend their time. As part of coursework focused on time management, students were asked to complete the survey once-per-day for five days during the fourth and seventh weeks of their first semester. These weeks were intentionally selected to allow students to be acclimated to the university experience while avoiding weeks of peak work. We used statistical analysis (n=75) to investigate two questions: How do first-year engineering students use their time? How do students' time-use profiles evolve during the semester? Using k-means clustering, analysis of variance, and pairwise comparisons we found three different time-profiles (assignment flexible, downtime flexible, and regulated), which generally held the same characteristics over the two weeks. Additionally, we found that nearly half of the students transitioned between clusters from between the fourth and seventh weeks. No clusters reported co-curricular involvement as a significant activity. Limited engagement in co-curriculars has been attributed to the rigors of the engineering curriculum and students' perceptions about the time required for involvement. Yet, little is known about how students spend their time, limiting our ability to develop interventions or policies that improve access to co-curriculars. While exploratory, our analysis suggests that even as time necessary for curricular obligations fluctuates, students may lack interest or ability to allocate time to co-curriculars. Situated among first-year students, one implication of this work is that supporting engagement in co-curriculars may best be accomplished through interventions that help students in developing routine. Additionally, implications as it pertains to pedagogical design and developing more equitable engineering programs are considered.

Application of the pathfinder landing system design to enclose the much larger Mars Exploration Rover required a variety of rover deployments to achieve the surface driving configuration. The project schedule demanded that software, design, engineering model test, and flight hardware build be accomplished in parallel. This challenge was met through (a) bounding unknown environments against which to design and test, (b) early mechanical prototype testing, (c) constraining the scope of on-board autonomy to survival-critical deployments, (d) executing a balance of nominal and off-nominal test cases, (e) developing off-nominal event mitigation techniques before landing, (f) flexible replanning in response to surprises during operations. Here is discussed several specific events encountered during initial MER surface operations.