SDValue.com - Risk and Fraud Analytics

Banking and Credit command center, robust internal controls and risk management system

Analyze exposure, occurrence and impact; improve risk insight, intelligence, management and planning; and streamline capital and risk reporting to reduce residual risk and align with BCBS driven principles.

What

Support in identifying, monitoring, quantifying and preventing fraud and risky events, across the banking lines of business:

Organization risk IQ
Credit risk modeling
Risk data aggregation
Fraud and anomaly detection

For whom

Leaders in the analytics, compliance, risk, audit, and internal control functions involved with monitoring and prudential initiatives in the retail banking division, including Digital, Hybrid and Traditional institutions.

VP, CFO, CRO, Director, CIO, Audit, Treasury, and Chief Analytics Officer.

Scope

The intervention can take one or more of the following forms:

Research and analysis,
Modeling and simulation
Deep-dive and experimentation

and can be extended, when requested by the client, to:

Developing and scaling an automated analytical process within the bank's Risk information system.

Why

To improve regulatory compliance, avoid unnecessary risks, and enable critical and risk-savvy decision making across the lines of business, with better control points, review processes and timely information for Risk, Compliance and Strategy teams to act on.

Use Cases:

> Credit risk aggregation and dashboard

Creating a control tower view over the aggregated risk data, lines of defense, and control points, with the ability to drill-down and roll-up to the granular components of risk data.
Refining the Key Risk Indicators (KRIs) and Key Control Indicators (KCIs), and increasing information quality, reliability and transparency into risk and capital performance reporting

> Internal rating-based approach to credit modeling

To calculate the Risk Weighted Assets for an aggregate consumer credit portfolio of a lending institution, a key challenge is to quantify the credit risk of each exposure in the portfolio. BCBS allows two options in this case: the (1) Standardized approach and the (2) IRB approach.
As the Advanced IRB approach is the most risk-sensitive and representative of member pools, segments and territories served by the institution, we have developed the data and analytics pipeline that enables our partner to derive its own assessment of the risk components using common statistical methodology.
We also explored an experimental approach of using Artificial Neural Networks to refine the probabilities and early signs of delinquency.