close button

Back

logologo

Bank reduces risk exposure, boosts return on capital

How a large private sector bank in India built an Early Warning System (EWS) to gauge and assign risk score. 

card
  • down-whiteClient
  • line-midChallenge
  • line-midSolution
  • line-midImpact
  • line-midConclusion

Client

Banks operate in a high-risk environment and require solutions that can proactively detect and prevent fraud, manage risks, and ensure secure and efficient banking operations. Early Warning Systems (EWS) have proven helpful in this case. Our client, a large private sector bank in India, wanted to build an Early Warning System (EWS) for its corporate clients that could automatically gauge and assign a risk score, probability of default, and EWS rating.

Challenge

The client embarked on an initiative to develop an Early Warning Scorecard (EWS). The requirements included automatically assigning risk scores, Probability of Default (PD), and EWS ratings, and automatic assignment of borrowers to standard, watch list, and exit categories. Additionally, the solution needed to get accurate individual Early Warning Indicators (EWIs) used in the scorecard, down to individual facility-level data where applicable. However, the project encountered several challenges, including four years’ worth of massive volumes of historic month-end data. Other issues included the need to identify historic cases beyond Non-Performing Assets (NPAs) and restructured cases, as well as calculate Max Customer Days Past Due (DPD) while excluding specific products from the calculation. Despite these challenges, the client successfully implemented a statistical EWS scorecard using a generalized linear model, identified significant EWIs through power analysis and correlation analysis, and achieved business benefits related to risk reduction and proactive account management.
Their challenges included:
1

Historic month-end data collection spanning four years

2

Need to identify historic cases that were considered ‘bad’ due to significant weaknesses observed

3

Need to compute Max Customer DPD to exclude specific products from the DPD computation

Solution

The bank chose to partner with BCT to develop an Early Warning System (EWS) that automatically assesses risk scores, probability of default, and EWS ratings for its corporate clients. The solution involved creating a statistical EWS scorecard using a generalized linear model. By identifying significant Early Warning Indicators (EWIs) through power analysis, correlation analysis, and economic logic, the bank achieved proactive identification of weak accounts. The system also facilitated automatic tracking of key EWIs from the core banking system, enabling timely updates to risk scores. As a result, the bank could manage non-performing assets (NPAs), optimize return on capital, and enhance the performance of its borrower rating model. Throughout this initiative, BCT ensured the following:
1

Created a statistical EWS scorecard using a generalized linear model

2

Identified EWIs using power analysis, correlation analysis, and economic logic

3

Identified six variables in the final scorecard covering transformed variables related to delinquency, credits in revolving accounts, overdrafts, check returns, etc.

4

Enabled scorecard scaling, calibration, bucketing, and exit/watch list thresholds

5

Enabled the tracking of all key EWIs from the core banking system

Impact

BCT’s creation and implementation of an Early Warning System (EWS) for the bank yielded significant business benefits. By automatically assigning risk scores, Probability of Default (PD), and EWS ratings, the bank proactively identifies weak accounts. This approach enables risk reduction, effective management of non-performing assets (NPAs), and optimization of return on capital. Additionally, the automatic tracking of key Early Warning Indicators (EWIs) from the core banking system ensures that relevant data is readily available, enabling regular score updates. Furthermore, by proactively identifying accounts for downgrade, the solution has enhanced the performance of the borrower rating model. With the newly built EWS, the client achieved the following:
1

Reduced risk exposures, better management of NPA, and optimized return on capital.

2

Regularly updated scores as relevant data is readily available.

3

Improved performance of borrower rating model.

Conclusion

By entering into a strategic technology partnership with BCT, the bank could successfully build an Early Warning System (EWS) that delivered significant business value. With BCT's dedicated support and expertise, the bank effectively implemented the solution, automating risk assessment for its corporate clients. Overcoming all data challenges, BCT developed a scorecard using a generalized linear model, enhancing risk management and NPA optimization. The EWS implementation has improved the bank’s borrower rating model, enabling proactive account downgrading and capital return optimization.

down-arrow

148, Rajiv Gandhi Salai(OMR), Okkiyam Thoraipakkam, Chennai - 600 097

down-arrow

+91 44 43449000,
+91 44 61739000

down-arrow

global@bahwancybertek.com

Bahwan CyberTek is a global technology transformation partner, driving innovation and equipping companies for the future.

© 2025 Bahwan CyberTek. All rights reserved.

Terms & Conditions 
Privacy Policy