9th International Conference on ICT for Sustainable Development

Authors - Kranti Shingate, Veena Grover, Shivi Khanna, Gaurav Gupta, Pradeep Chintale, HarshaVardhan Nerella, CH Vanipriya, Saikat Gochhait
Abstract - Business processes have been transformed with the advent of Artificial intelligence. However, to efficiently utilize the technology and to close the gap, we reviewed the literature to find these solutions in this work. We ensured that styles worked because they allowed for extensions and replication. In these studies, we correlated patterns that assisted with task automation and helped analysts create, expand, or re- engineer business processes with the confidence to make judgments. The authors used various AI methods, including swarm intelligence, Bayesian networks, and K-means. Our analysis gives data on the approaches and issues being dealt with and indicates potential future directions. Processes for Predictive Business Future planning and activity prediction are examples of monitoring jobs that are becoming less significant as new technologies allow for the intelligent automation of company processes. Deep learning models are used in recent work on this subject to encapsulate historical event information without further processing. The data context, which includes the dependence of conditions and particular traits, might also have an impact on the anticipated data, even though it was not taken into account in earlier research. We present a novel encoding strategy for state data, encompassing non-existent, multi-character private, and regular event states. We present the Transformer and LSTM deep learning models, two new deep learning models, two popular deep learning models.