Chiara Ghidini

Patrizio Bellan, Han van der Aa, Mauro Dragoni et al.

Process extraction from text is an important task of process discovery, for which various approaches have been developed in recent years. However, in contrast to other information extraction tasks, there is a lack of gold-standard corpora of business process descriptions that are carefully annotated with all the entities and relationships of interest. Due to this, it is currently hard to compare the results obtained by extraction approaches in an objective manner, whereas the lack of annotated texts also prevents the application of data-driven information extraction methodologies, typical of the natural language processing field. Therefore, to bridge this gap, we present the PET dataset, a first corpus of business process descriptions annotated with activities, gateways, actors, and flow information. We present our new resource, including a variety of baselines to benchmark the difficulty and challenges of business process extraction from text. PET can be accessed via huggingface.co/datasets/patriziobellan/PET

Marco Roveri, Claudio Di Ciccio, Chiara Di Francescomarino et al.

Linear-time temporal logic on finite traces (LTLf) is rapidly becoming a de-facto standard to produce specifications in many application domains (e.g., planning, business process management, run-time monitoring, reactive synthesis). Several studies approached the respective satisfiability problem. In this paper, we investigate the problem of extracting the unsatisfiable core in LTLf specifications. We provide four algorithms for extracting an unsatisfiable core leveraging the adaptation of state-of-the-art approaches to LTLf satisfiability checking. We implement the different approaches within the respective tools and carry out an experimental evaluation on a set of reference benchmarks, restricting to the unsatisfiable ones. The results show the feasibility, effectiveness, and complementarities of the different algorithms and tools.

Stefano Branchi, Andrei Buliga, Chiara Di Francescomarino et al.

Prescriptive Process Monitoring is a prominent problem in Process Mining, which consists in identifying a set of actions to be recommended with the goal of optimising a target measure of interest or Key Performance Indicator (KPI). One challenge that makes this problem difficult is the need to provide Prescriptive Process Monitoring techniques only based on temporally annotated (process) execution data, stored in, so-called execution logs, due to the lack of well crafted and human validated explicit models. In this paper we aim at proposing an AI based approach that learns, by means of Reinforcement Learning (RL), an optimal policy (almost) only from the observation of past executions and recommends the best activities to carry on for optimizing a KPI of interest. This is achieved first by learning a Markov Decision Process for the specific KPIs from data, and then by using RL training to learn the optimal policy. The approach is validated on real and synthetic datasets and compared with off-policy Deep RL approaches. The ability of our approach to compare with, and often overcome, Deep RL approaches provides a contribution towards the exploitation of white box RL techniques in scenarios where only temporal execution data are available.

Stefano Branchi, Chiara Di Francescomarino, Chiara Ghidini et al.

The rise of process data availability has recently led to the development of data-driven learning approaches. However, most of these approaches restrict the use of the learned model to predict the future of ongoing process executions. The goal of this paper is moving a step forward and leveraging available data to learning to act, by supporting users with recommendations derived from an optimal strategy (measure of performance). We take the optimization perspective of one process actor and we recommend the best activities to execute next, in response to what happens in a complex external environment, where there is no control on exogenous factors. To this aim, we investigate an approach that learns, by means of Reinforcement Learning, the optimal policy from the observation of past executions and recommends the best activities to carry on for optimizing a Key Performance Indicator of interest. The validity of the approach is demonstrated on two scenarios taken from real-life data.

Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini et al.

Predictive Process Monitoring is a field of Process Mining that aims at predicting how an ongoing execution of a business process will develop in the future using past process executions recorded in event logs. The recent stream of publications in this field shows the need for tools able to support researchers and users in analyzing, comparing and selecting the techniques that are the most suitable for them. Nirdizati is a dedicated tool for supporting users in building, comparing, analyzing, and explaining predictive models that can then be used to perform predictions on the future of an ongoing case. By providing a rich set of different state-of-the-art approaches, Nirdizati offers BPM researchers and practitioners a useful and flexible instrument for investigating and comparing Predictive Process Monitoring techniques. In this paper, we present the current version of Nirdizati, together with its architecture which has been developed to improve its modularity and scalability. The features of Nirdizati enrich its capability to support researchers and practitioners within the entire pipeline for constructing reliable Predictive Process Monitoring models.

Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini et al.

Recent papers have introduced a novel approach to explain why a Predictive Process Monitoring (PPM) model for outcome-oriented predictions provides wrong predictions. Moreover, they have shown how to exploit the explanations, obtained using state-of-the art post-hoc explainers, to identify the most common features that induce a predictor to make mistakes in a semi-automated way, and, in turn, to reduce the impact of those features and increase the accuracy of the predictive model. This work starts from the assumption that frequent control flow patterns in event logs may represent important features that characterize, and therefore explain, a certain prediction. Therefore, in this paper, we (i) employ a novel encoding able to leverage DECLARE constraints in Predictive Process Monitoring and compare the effectiveness of this encoding with Predictive Process Monitoring state-of-the art encodings, in particular for the task of outcome-oriented predictions; (ii) introduce a completely automated pipeline for the identification of the most common features inducing a predictor to make mistakes; and (iii) show the effectiveness of the proposed pipeline in increasing the accuracy of the predictive model by validating it on different real-life datasets.

Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini et al.

Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods do not readily apply to temporal domains, such as that of process mining, where data take the form of traces of activities that must obey to temporal background knowledge expressing which dynamics are possible and which not. Specifically, counterfactuals generated off-the-shelf may violate the background knowledge, leading to inconsistent explanations. This work tackles this challenge by introducing a novel approach for generating temporally constrained counterfactuals, guaranteed to comply by design with background knowledge expressed in Linear Temporal Logic on process traces (LTLp). We do so by infusing automata-theoretic techniques for LTLp inside a genetic algorithm for counterfactual generation. The empirical evaluation shows that the generated counterfactuals are temporally meaningful and more interpretable for applications involving temporal dependencies.

Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini et al.

Counterfactual explanations suggest what should be different in the input instance to change the outcome of an AI system. When dealing with counterfactual explanations in the field of Predictive Process Monitoring, however, control flow relationships among events have to be carefully considered. A counterfactual, indeed, should not violate control flow relationships among activities (temporal background knowledege). Within the field of Explainability in Predictive Process Monitoring, there have been a series of works regarding counterfactual explanations for outcome-based predictions. However, none of them consider the inclusion of temporal background knowledge when generating these counterfactuals. In this work, we adapt state-of-the-art techniques for counterfactual generation in the domain of XAI that are based on genetic algorithms to consider a series of temporal constraints at runtime. We assume that this temporal background knowledge is given, and we adapt the fitness function, as well as the crossover and mutation operators, to maintain the satisfaction of the constraints. The proposed methods are evaluated with respect to state-of-the-art genetic algorithms for counterfactual generation and the results are presented. We showcase that the inclusion of temporal background knowledge allows the generation of counterfactuals more conformant to the temporal background knowledge, without however losing in terms of the counterfactual traditional quality metrics.

Riccardo Graziosi, Massimiliano Ronzani, Andrei Buliga et al.

In recent years, trace generation has emerged as a significant challenge within the Process Mining community. Deep Learning (DL) models have demonstrated accuracy in reproducing the features of the selected processes. However, current DL generative models are limited in their ability to adapt the learned distributions to generate data samples based on specific conditions or attributes. This limitation is particularly significant because the ability to control the type of generated data can be beneficial in various contexts, enabling a focus on specific behaviours, exploration of infrequent patterns, or simulation of alternative 'what-if' scenarios. In this work, we address this challenge by introducing a conditional model for process data generation based on a conditional variational autoencoder (CVAE). Conditional models offer control over the generation process by tuning input conditional variables, enabling more targeted and controlled data generation. Unlike other domains, CVAE for process mining faces specific challenges due to the multiperspective nature of the data and the need to adhere to control-flow rules while ensuring data variability. Specifically, we focus on generating process executions conditioned on control flow and temporal features of the trace, allowing us to produce traces for specific, identified sub-processes. The generated traces are then evaluated using common metrics for generative model assessment, along with additional metrics to evaluate the quality of the conditional generation

Riccardo Andreoni, Andrei Buliga, Alessandro Daniele et al.

State-of-the-art approaches for integrating symbolic knowledge with deep learning architectures have demonstrated promising results in static domains. However, methods to handle temporal logic specifications remain underexplored. The only existing approach relies on an explicit representation of a finite-state automaton corresponding to the temporal specification. Instead, we aim at proposing a neurosymbolic framework designed to incorporate temporal logic specifications, expressed in Linear Temporal Logic over finite traces (LTLf), directly into deep learning architectures for sequence-based tasks. We extend the Iterative Local Refinement (ILR) neurosymbolic algorithm, leveraging the recent introduction of fuzzy LTLf interpretations. We name this proposed method Temporal Iterative Local Refinement (T-ILR). We assess T-ILR on an existing benchmark for temporal neurosymbolic architectures, consisting of the classification of image sequences in the presence of temporal knowledge. The results demonstrate improved accuracy and computational efficiency compared to the state-of-the-art method.

Patrizio Bellan, Mauro Dragoni, Chiara Ghidini

Recent advances in Natural Language Processing, and in particular on the construction of very large pre-trained language representation models, is opening up new perspectives on the construction of conversational information seeking (CIS) systems. In this paper we investigate the usage of in-context learning and pre-trained language representation models to address the problem of information extraction from process description documents, in an incremental question and answering oriented fashion. In particular we investigate the usage of the native GPT-3 (Generative Pre-trained Transformer 3) model, together with two in-context learning customizations that inject conceptual definitions and a limited number of samples in a few shot-learning fashion. The results highlight the potential of the approach and the usefulness of the in-context learning customizations, which can substantially contribute to address the "training data challenge" of deep learning based NLP techniques the BPM field. It also highlight the challenge posed by control flow relations for which further training needs to be devised.

Williams Rizzi, Marco Comuzzi, Chiara Di Francescomarino et al.

Explainability is motivated by the lack of transparency of black-box Machine Learning approaches, which do not foster trust and acceptance of Machine Learning algorithms. This also happens in the Predictive Process Monitoring field, where predictions, obtained by applying Machine Learning techniques, need to be explained to users, so as to gain their trust and acceptance. In this work, we carry on a user evaluation on explanation approaches for Predictive Process Monitoring aiming at investigating whether and how the explanations provided (i) are understandable; (ii) are useful in decision making tasks;(iii) can be further improved for process analysts, with different Machine Learning expertise levels. The results of the user evaluation show that, although explanation plots are overall understandable and useful for decision making tasks for Business Process Management users -- with and without experience in Machine Learning -- differences exist in the comprehension and usage of different plots, as well as in the way users with different Machine Learning expertise understand and use them.

Giacomo Bergami, Chiara Di Francescomarino, Chiara Ghidini et al.

Business process deviance refers to the phenomenon whereby a subset of the executions of a business process deviate, in a negative or positive way, with respect to {their} expected or desirable outcomes. Deviant executions of a business process include those that violate compliance rules, or executions that undershoot or exceed performance targets. Deviance mining is concerned with uncovering the reasons for deviant executions by analyzing event logs stored by the systems supporting the execution of a business process. In this paper, the problem of explaining deviations in business processes is first investigated by using features based on sequential and declarative patterns, and a combination of them. Then, the explanations are further improved by leveraging the data attributes of events and traces in event logs through features based on pure data attribute values and data-aware declarative rules. The explanations characterizing the deviances are then extracted by direct and indirect methods for rule induction. Using real-life logs from multiple domains, a range of feature types and different forms of decision rules are evaluated in terms of their ability to accurately discriminate between non-deviant and deviant executions of a process as well as in terms of understandability of the final outcome returned to the users.

Patrizio Bellan, Mauro Dragoni, Chiara Ghidini et al.

The extraction of process models from text refers to the problem of turning the information contained in an unstructured textual process descriptions into a formal representation,i.e.,a process model. Several automated approaches have been proposed to tackle this problem, but they are highly heterogeneous in scope and underlying assumptions,i.e., differences in input, target output, and data used in their evaluation.As a result, it is currently unclear how well existing solutions are able to solve the model-extraction problem and how they compare to each other.We overcome this issue by comparing 10 state-of-the-art approaches for model extraction in a systematic manner, covering both qualitative and quantitative aspects.The qualitative evaluation compares the analysis of the primary studies on: 1 the main characteristics of each solution;2 the type of process model elements extracted from the input data;3 the experimental evaluation performed to evaluate the proposed framework.The results show a heterogeneity of techniques, elements extracted and evaluations conducted, that are often impossible to compare.To overcome this difficulty we propose a quantitative comparison of the tools proposed by the papers on the unifying task of process model entity and relation extraction so as to be able to compare them directly.The results show three distinct groups of tools in terms of performance, with no tool obtaining very good scores and also serious limitations.Moreover, the proposed evaluation pipeline can be considered a reference task on a well-defined dataset and metrics that can be used to compare new tools. The paper also presents a reflection on the results of the qualitative and quantitative evaluation on the limitations and challenges that the community needs to address in the future to produce significant advances in this area.

Federico Chesani, Chiara Di Francescomarino, Chiara Ghidini et al.

As the need to understand and formalise business processes into a model has grown over the last years, the process discovery research field has gained more and more importance, developing two different classes of approaches to model representation: procedural and declarative. Orthogonally to this classification, the vast majority of works envisage the discovery task as a one-class supervised learning process guided by the traces that are recorded into an input log. In this work instead, we focus on declarative processes and embrace the less-popular view of process discovery as a binary supervised learning task, where the input log reports both examples of the normal system execution, and traces representing "stranger" behaviours according to the domain semantics. We therefore deepen how the valuable information brought by both these two sets can be extracted and formalised into a model that is "optimal" according to user-defined goals. Our approach, namely NegDis, is evaluated w.r.t. other relevant works in this field, and shows promising results as regards both the performance and the quality of the obtained solution.

Chiara Ghidini, Marco Rospocher, Luciano Serafini

In this paper we present a textual description, in terms of Description Logics, of the BPMN Ontology, which provides a clear semantic formalisation of the structural components of the Business Process Modelling Notation (BPMN), based on the latest stable BPMN specifications from OMG [BPMN Version 1.1 -- January 2008]. The development of the ontology was guided by the description of the complete set of BPMN Element Attributes and Types contained in Annex B of the BPMN specifications.

Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini et al.

Existing well investigated Predictive Process Monitoring techniques typically construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating it with new cases when they complete their execution. This can make Predictive Process Monitoring too rigid to deal with the variability of processes working in real environments that continuously evolve and/or exhibit new variant behaviours over time. As a solution to this problem, we evaluate the use of three different strategies that allow the periodic rediscovery or incremental construction of the predictive model so as to exploit new available data. The evaluation focuses on the performance of the new learned predictive models, in terms of accuracy and time, against the original one, and uses a number of real and synthetic datasets with and without explicit Concept Drift. The results provide an evidence of the potential of incremental learning algorithms for predicting process monitoring in real environments.

Greta Adamo, Chiara Ghidini, Chiara Di Francescomarino

Business process modelling languages typically enable the representation of business process models by employing (graphical) symbols. These symbols can vary depending upon the verbosity of the language, the modelling paradigm, the focus of the language, and so on. To make explicit the different constructs and rules employed by a specific language, as well as bridge the gap across different languages, meta-models have been proposed in literature. These meta-models are a crucial source of knowledge on what state-of-the-art literature considers relevant to describe business processes. The goal of this work is to provide an extensive systematic literature review (SLR) of business process meta-models. This SLR aims at answering research questions concerning: (i) the kind of meta-models proposed in literature; (ii) the recurring constructs they contain; (iii) their purposes; and (iv) their evaluations.

Riccardo De Masellis, Chiara Di Francescomarino, Chiara Ghidini et al.

Recent advances in the field of Business Process Management have brought about several suites able to model complex data objects along with the traditional control flow perspective. Nonetheless, when it comes to formal verification there is still the lack of effective verification tools on imperative data-aware process models and executions: the data perspective is often abstracted away and verification tools are often missing. In this paper we provide a concrete framework for formal verification of reachability properties on imperative data-aware business processes. We start with an expressive, yet empirically tractable class of data-aware process models, an extension of Workflow Nets, and we provide a rigorous mapping between the semantics of such models and that of three important paradigms for reasoning about dynamic systems: Action Languages, Classical Planning, and Model Checking. Then we perform a comprehensive assessment of the performance of three popular tools supporting the above paradigms in solving reachability problems for imperative data-aware business processes, which paves the way for a theoretically well founded and practically viable exploitation of formal verification techniques on data-aware business processes.

Chiara Di Francescomarino, Chiara Ghidini, Fabrizio Maria Maggi et al.

A characteristic of existing predictive process monitoring techniques is to first construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating it with new cases when they complete their execution. This can make predictive process monitoring too rigid to deal with the variability of processes working in real environments that continuously evolve and/or exhibit new variant behaviors over time. As a solution to this problem, we propose the use of algorithms that allow the incremental construction of the predictive model. These incremental learning algorithms update the model whenever new cases become available so that the predictive model evolves over time to fit the current circumstances. The algorithms have been implemented using different case encoding strategies and evaluated on a number of real and synthetic datasets. The results provide a first evidence of the potential of incremental learning strategies for predicting process monitoring in real environments, and of the impact of different case encoding strategies in this setting.

Chiara Di Francescomarino, Chiara Ghidini, Fabrizio Maria Maggi et al.

Predictive process monitoring has recently gained traction in academia and is maturing also in companies. However, with the growing body of research, it might be daunting for companies to navigate in this domain in order to find, provided certain data, what can be predicted and what methods to use. The main objective of this paper is developing a value-driven framework for classifying existing work on predictive process monitoring. This objective is achieved by systematically identifying, categorizing, and analyzing existing approaches for predictive process monitoring. The review is then used to develop a value-driven framework that can support organizations to navigate in the predictive process monitoring field and help them to find value and exploit the opportunities enabled by these analysis techniques.

Riccardo De Masellis, Chiara Di Francescomarino, Chiara Ghidini et al.

The growing adoption of IT-systems for modeling and executing (business) processes or services has thrust the scientific investigation towards techniques and tools which support more complex forms of process analysis. Many of them, such as conformance checking, process alignment, mining and enhancement, rely on complete observation of past (tracked and logged) executions. In many real cases, however, the lack of human or IT-support on all the steps of process execution, as well as information hiding and abstraction of model and data, result in incomplete log information of both data and activities. This paper tackles the issue of automatically repairing traces with missing information by notably considering not only activities but also data manipulated by them. Our technique recasts such a problem in a reachability problem and provides an encoding in an action language which allows to virtually use any state-of-the-art planning to return solutions.

Wil M. P. van der Aalst, Riccardo De Masellis, Chiara Di Francescomarino et al.

Process discovery techniques return process models that are either formal (precisely describing the possible behaviors) or informal (merely a "picture" not allowing for any form of formal reasoning). Formal models are able to classify traces (i.e., sequences of events) as fitting or non-fitting. Most process mining approaches described in the literature produce such models. This is in stark contrast with the over 25 available commercial process mining tools that only discover informal process models that remain deliberately vague on the precise set of possible traces. There are two main reasons why vendors resort to such models: scalability and simplicity. In this paper, we propose to combine the best of both worlds: discovering hybrid process models that have formal and informal elements. As a proof of concept we present a discovery technique based on hybrid Petri nets. These models allow for formal reasoning, but also reveal information that cannot be captured in mainstream formal models. A novel discovery algorithm returning hybrid Petri nets has been implemented in ProM and has been applied to several real-life event logs. The results clearly demonstrate the advantages of remaining "vague" when there is not enough "evidence" in the data or standard modeling constructs do not "fit". Moreover, the approach is scalable enough to be incorporated in industrial-strength process mining tools.

Giulio Petrucci, Chiara Ghidini, Marco Rospocher

Recently, Neural Networks have been proven extremely effective in many natural language processing tasks such as sentiment analysis, question answering, or machine translation. Aiming to exploit such advantages in the Ontology Learning process, in this technical report we present a detailed description of a Recurrent Neural Network based system to be used to pursue such goal.

Federico Chesani, Riccardo De Masellis, Chiara Di Francescomarino et al.

The capability to store data about business processes execution in so-called Event Logs has brought to the diffusion of tools for the analysis of process executions and for the assessment of the goodness of a process model. Nonetheless, these tools are often very rigid in dealing with with Event Logs that include incomplete information about the process execution. Thus, while the ability of handling incomplete event data is one of the challenges mentioned in the process mining manifesto, the evaluation of compliance of an execution trace still requires an end-to-end complete trace to be performed. This paper exploits the power of abduction to provide a flexible, yet computationally effective, framework to deal with different forms of incompleteness in an Event Log. Moreover it proposes a refinement of the classical notion of compliance into strong and conditional compliance to take into account incomplete logs. Finally, performances evaluation in an experimental setting shows the feasibility of the presented approach.

Riccardo De Masellis, Chiara Ghidini, Silvio Ranise

Purpose is crucial for privacy protection as it makes users confident that their personal data are processed as intended. Available proposals for the specification and enforcement of purpose-aware policies are unsatisfactory for their ambiguous semantics of purposes and/or lack of support to the run-time enforcement of policies. In this paper, we propose a declarative framework based on a first-order temporal logic that allows us to give a precise semantics to purpose-aware policies and to reuse algorithms for the design of a run-time monitor enforcing purpose-aware policies. We also show the complexity of the generation and use of the monitor which, to the best of our knowledge, is the first such a result in literature on purpose-aware policies.

Fabrizio Maria Maggi, Chiara Di Francescomarino, Marlon Dumas et al.

Modern information systems that support complex business processes generally maintain significant amounts of process execution data, particularly records of events corresponding to the execution of activities (event logs). In this paper, we present an approach to analyze such event logs in order to predictively monitor business goals during business process execution. At any point during an execution of a process, the user can define business goals in the form of linear temporal logic rules. When an activity is being executed, the framework identifies input data values that are more (or less) likely to lead to the achievement of each business goal. Unlike reactive compliance monitoring approaches that detect violations only after they have occurred, our predictive monitoring approach provides early advice so that users can steer ongoing process executions towards the achievement of business goals. In other words, violations are predicted (and potentially prevented) rather than merely detected. The approach has been implemented in the ProM process mining toolset and validated on a real-life log pertaining to the treatment of cancer patients in a large hospital.