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

Vincenzo Pasquadibisceglie,Donato Malerba,Giuseppe Modugno,Giovanna Castellano,Annalisa Appice

doi:10.1109/access.2020.3029323

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.

Highlights

Nowadays predictive process mining is playing a fundamental role in the business scenario
The proposed method, called ORANGE (Outcome pRediction bAsed oN imaGe Encoding) adopts an imagery representation of ongoing traces, which is able to delineate potential data patterns that arise at neighbour pixels representing trace features
We propose a novel deep learning approach called ORANGE (Outcome pRediction bAsed oN imaGe Encoding)

Summary

Introduction

Nowadays predictive process mining is playing a fundamental role in the business scenario. The proposed method, called ORANGE (Outcome pRediction bAsed oN imaGe Encoding) adopts an imagery representation of ongoing traces, which is able to delineate potential data patterns that arise at neighbour pixels representing trace features. This result is achieved once a vector of trace features is extracted and arranged as pixel frames of an image and CNNs are trained to address the outcome monitoring process as a problem of image classification.

Results

Conclusion