ORANGE: Outcome-Oriented Predictive Process Monitoring Based on Image Encoding and CNNs

Abstract

The outcome-oriented predictive process monitoring is a family of predictive process mining techniques that have witnessed rapid development and increasing adoption in the past few years. Boosted by the recent successful applications of deep learning in predictive process mining, we propose ORANGE, a novel deep learning method for learning outcome-oriented predictive process models. The main innovation of this study is that we adopt an imagery representation of the ongoing traces, which delineates potential data patterns that arise at neighbour pixels. Leveraging a collection of images representing ongoing traces, we train a Convolutional Neural Network (CNN) to predict the outcome of an ongoing trace. The empirical study shows the feasibility of the proposed method by investigating its accuracy on different benchmark outcome prediction problems in comparison to state-of-art competitor methods. In addition, we show how ORANGE can be integrated as an Intelligent Assistant into a CVM realized by MTM Project srl company to support sales agents in their negotiations. This case study shows that ORANGE can be effectively used to smartly monitor the outcome of ongoing negotiations by early highlighting negotiations that are candidate to be completed successfully. INDEX TERMS Predictive process analytics; Outcome prediction; Computer vision, Convolutional neural networks; Spatial data modeling.

Stability Metrics for Enhancing the Evaluation of Outcome-Based Business Process Predictive Monitoring

“…Tree-based classifiers such as random forest or extreme gradient boosting have successfully been adopted to predict process outcomes along with various bucketing techniques, such as prefix-length bucketing or clustering bucketing, and sequence encoding techniques such as indexbased encoding and Hidden Markov Models (HMM)-based encoding [17], [18]. Most recently, the focus of the research community appears to have shifted to complex deep learning architectures [19], [20], which however appear more suited to use cases such as next activity or time prediction, and to generating and interpreting explanations for the output of process predictive monitoring [21]- [23].…”

Multivariate Business Process Representation Learning utilizing Gramian Angular Fields and Convolutional Neural Networks

“…Other approaches for next step prediction used different techniques such as decision trees (DT ) [9], autoencoder (AE ) with n-grams [10], attention networks [12], CNNs [18] or generative adversarial networks (GAN ) [24]. Similarly, CNNs [19], LSTMs [14] or autoencoder [11] are used for outcome prediction. In order to detect anomalies in business process data, LSTMs [16] or Bayesian neural networks [20] were applied.…”

“…Current machine-learning-based methods for predictive problems on business process data, e.g., neural-network-based methods like LSTMs or CNNs, achieve high accuracies in many tasks such as next activity prediction or remaining time prediction on many publicly available datasets [15]. In recent time, a large variety of new architectures for next step and outcome prediction have been proposed and evaluated [19,17,24]. These machine-learning-based methods are mostly task-specific and not generic, i.e., they are designed and tested on predictive process analytics tasks like next step prediction, outcome prediction, anomaly detection, or clustering.…”

DeepInsight-3D for precision oncology: an improved anti-cancer drug response prediction from high-dimensional multi-omics data with convolutional neural networks

“…The DeepInsight method pioneered a strategy by converting non-image data to image form and then processing it to CNN for classification for various kinds of datasets. It has been widely used in various fields such as in cancer research [10][11][12], viral infections [13], sparse data [14], power energy [15], business and manufacturing [16], time-series data [17][18][19], traffic cash analysis [20], human activity recognition [21], feature representation [22], intrusion detection [23], spine surgery [24] and HVAC fault diagnosis [25]. Moreover, DeepInsight was a component in the Kaggle.com competition hosted by MIT and Harvard University that secured rank1 on the leaderboard [26].…”