Diving Deeper

Increasing Confidence in Model Performance Monitoring Through Automation

When an information services company discovered its model monitoring process was fraught with inefficiencies and roadblocks, they needed to redesign the platform to support automation, provide confidence in results, and facilitate widespread adoption throughout the organization.

Case Study: The solution, which reduced the cost and improved the efficiency of model performance monitoring, eliminated single-person dependency to operate the process, reduced the number of analysts needed to monitor the model, and dramatically enhanced the coverage and speed of the execution cycle. A top-to-bottom audit of the new model performancemonitoring process within months of implementation resulted in no findings, giving leadership comfort in the rigor and reliability of the system and confidence to act on modeling insights that drive business.

Reducing Risk, Lowering Cost in Credit Card Authorization Decisions

Having already invested heavily to create a robust authorization platform, the bank was prepared to increase its stake in technology with an additional $1.2M. After investigating the problem, Flying Phase provided the bank with a roadmap to save between $500K and $1M in fraud costs and credit-risk approvals by rebuilding the back-up decision logic found within the third-party processor.

Case Study: A top 10 bank that processed more than seven billion credit card transactions annually became concerned about its exposure to risk when it discovered that two million of those were decisioned with incomplete information. Having already invested heavily to create a robust authorization platform, the bank was prepared to increase its stake in technology with an additional $1.2M. After investigating the problem, Flying Phase provided the bank with a roadmap to save between $500K and $1M in fraud costs and credit-risk approvals by rebuilding the back-up decision logic found within the third-party processor. It also re-allocated the $1.2M...

Leveraging Credit Expertise to Forecast Customer Hardship and Minimize Bank Charge-Offs

When the COVID-19 pandemic slowed the world’s economy to a crawl, many banks relied on models and forecasting to anticipate customer delinquencies and hardship and to efficiently staff its call centers.

Case Study:  The recoveries and customer support group at a Top 25 bank found itself facing a turbulent economic landscape in 2020 when the COVID-19 pandemic slowed the entire world’s economy to a crawl. When the COVID-19 pandemic slowed the world’s economy to a crawl, many banks relied on models and forecasting to anticipate customer hardship and efficiently staff its call centers. Appropriate staffing is critical for banks to effectively assist customers who have fallen behind in payments or who needed assistance with forbearance or deferral programs. This assistance helps customers get out of delinquency and avoid defaults, and helps...

Leveraging Data Infrastructure and Governance to Speed Model Development and Execution

Architected data platforms provide a foundation for automated modeling and forecasting to reduce cycle times and ensure well-managed data inputs.

Case Study: Architected data platforms provide a foundation for automated modeling and forecasting to reduce cycle times and ensure well-managed data inputs. The model development team at a Top 10 bank was responsible for forecasting on a $100 billion loan portfolio, but development efforts were often stalled by the complexity in data, and created compliance issues in the process. We implemented a data platform for providing authoritative and high-quality data to streamline the model development process and ensure the bank stays compliant and well-managed. Case Study: Leveraging Data Infrastructure and Governance to Speed Model Development and Execution

Building an Efficient and Compliant CCAR Modeling System

Robust coding practices and streamlining the process and reduces delays and errors in model development and implementation for critical CCAR stress testing execution.

Case Study: Robust coding practices and streamlining the process reduced delays and errors in model development and implementation for critical CCAR stress testing execution. Complex and unreliable code, manual processes, and extensive back-and-forth with development teams made it difficult for a Top 20 bank to implement models required for the Comprehensive Capital Analysis and Review (CCAR), a federal stress-testing exercise. The existing environment resulted in delays, data issues and model revisions that put the bank at risk for non-compliance in submitting on time. Facing multiple pain points with that process, the bank tapped into our expertise and experience to develop a...

Productionizing Allowance: An Engineering Approach to an Analytical Process

Bringing production quality methods and controls to the quarterly impairment allowance created a fully compliant allowance process that reduced cycle time and resource needs by 80%.

Case Study: Bringing production quality methods and controls to the quarterly impairment allowance created a fully compliant allowance process that reduced cycle time and resource needs by 80%. Several analyst teams at a Top 10 bank spent four weeks each quarter estimating the company's consumer loan impairment allowance, which represents capital to be set aside for expected losses on the bank's $100 billion loan portfolio. Manual, spreadsheet-based processes were labor-intensive and error prone, leading to delays and reduced confidence in the results. With these issues contributing to audit findings and potentially tens of millions of dollars in excess allowance, the...

Automation of Monitoring in Field Operations and Calculating Incentives

Automation delivers higher accuracy and speed in $60 million in annual incentive payouts to telecommunication field technicians.

Case Study: Automation delivers higher accuracy and speed in $60 million in annual incentive payouts to telecommunication field technicians. Cumbersome manual processes caused errors and delays in distributing $5 million in monthly incentives at a major telecommunications firm, leaving operations field managers and technicians disappointed in an exchange that was intended to drive engagement and morale. Every month, four teams worked with multiple disparate spreadsheet tools to pull data and calculate incentives, an unwieldy and risky approach that took more than 45 days to process payments Recognizing the need to streamline and improve this critical function, the firm turned to...

Superior Loss Forecasting Through Machine Learning

Automated machine learning solutions drive better modeling results and a more controlled process in loss forecasting.

Case Study: Automated machine learning solutions drive better modeling results and a more controlled process in loss forecasting. A Top 10 bank relied on traditional statistics to forecast credit losses and make decisions based on those insights. Their processes were labor-intensive and complex, and as a result did not deliver insights to leadership quickly enough to drive decision-making. We reimagined this process to create a simplified platform based on extreme automation and machine learning to deliver more accurate results in half the time. We gave leadership the insights and confidence to take action. Case Study: Superior Forecasting Through Machine Learning

BLOG > EXTREME AUTOMATION

The Process Behind Process Automation

From EUCs to structured, automated data, we walk you through the process, best practices and change management to ensure you’re leveraging analysts’ skillsets to the fullest.

Since its introduction in September 1987, Excel has been the go-to resource in an analyst’s toolkit due to its versatility and capacity to quickly translate complex formulas into illustrative tables and charts. Over the ensuing years, a typical financial services analyst would build elaborate, interwoven spreadsheets, simple models, assumptions and calculations, all in Excel, creating end-user computing (EUC) applications. And while these EUCs built the foundation for modern automation, generally speaking, they lacked traceability or documentation, making model adjustments challenging and presenting serious challenges for governance, risk and regulatory compliance functions.