Paper Title
Predictive Machine Learning For Recommendation System In Big Data Unstructured Business Processes

Abstract
In the current era of Big Data, mutations in Business Process Management (BPM) remain poorly understood where organizations are confronted to a growing complexity of Business Processes (BP). Due to continuous and incessant of unexpected changes, Unstructured Business Processes (UBP) become the most crucial issues in the area of Big Data business management. The proposed approach in this paper introduces a new Machine Learning (ML) approach, able to optimize unexpected exceptions, and reduce time-consuming in UBP. A new Reinforcement Learning algorithm is proposed to predict the best action to undertake and avoid unexpected paths in a recommending aid-to-system architecture. For empirical proof, a simulation case study is applied with key findings and validation outcomes. The results reveal how the method can preserve robustness despite unpredicted alterations. Moreover, this paper provides large spectra of academic bibliography as an interesting background for UBP, which still a rarely discussed topic in research works. Index Terms - Prediction, Machine Learning, Big Data, Business Process Management.