Accounting & Finance
❯
Reduce Fraud
❯Accounting and Finance - Reduce Fraud
Leapfrogging Fraud Detection in Banking: Transition from rule-based to AI approach
For:
- Banking and Financial Service providers
- Auditors
Goal:
Anticipate Risks
Large Companies
Accounting and Finance - Reduce Fraud
For:
Financial Controllers, bank managers
Scope:
Using Machine Learning and Natural Language Processing to improve the accuracy of suspicious activity reporting at a bank.
Goal:
Improved Operation
Detection of frauds based on collusions
For:
Stock market regulator, stock traders, stock investors
Scope:
Validating the predicted collusion set is effort-intensive and investigative and
legal expertise are necessary
Goal:
Automate a Business Process
Large Companies
Accounting and Finance - Reduce Fraud
For:
Financial Controllers, bank managersGoal:
Improved OperationProblem addressed
Anti Money Laundering (AML) refers to the laws, regulations and procedures aimed at uncovering efforts to disguise illicit funds as legitimate income. Financial institutions are obliged to file suspicious activity reports (SAR) whenever transactions appear abnormal, such as unusually large transfer amounts.
Challenges include dealing with a large number of potential false positive detections of suspicious activity that weigh on resources, the often disparate data sources required to be aggregated in order to recognise suspicious activity, and the resource burden of filing SARs.
Scope of use case
Using Machine Learning and Natural Language Processing to improve the accuracy of suspicious activity reporting at a bank.
Raw Data
Text
AI: Perceive
Machine Learning
NLP
AI: Understand
Detect Anomaly & Fraud
AI: Act