AI-Driven Predictive Financial Intelligence

Read full text Summarise with VIRAT
Authors: Jayarami Reddy Pullareddy
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper is based on a recurring problem I encountered in SAP finance programs: controllers had more data than time, but no consistent way to rank the items that required attention. The Predictive Financial Intelligence (PFI) design uses ACDOCA and BKPF data, close-status signals, and entity-specific features to score journal anomalies, close risk, and forecast variance. The score then passes through finance policy before any action is created. The paper provides the data contract, scoring logic, workflow evidence, pilot measures, and monitoring controls required for implementation. The perspective is grounded in transformation work where standardized calendars and automation helped move close completion from approximately workday five to workday three, and where inbound bank files moved from recurring manual handling to automated integration. Those outcomes motivate the design but are not presented as results caused by the predictive model.

Fields of Study & Subjects

ERP Systems Implementation and Impact Robotic Process Automation Applications Big Data and Business Intelligence

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN
Document type
Preprint