Applied Informatics for Credit Risk, Consumer Lending & Portfolio Intelligence

Turning lending data into measurable decisions from underwriting strategy and scorecards to portfolio monitoring,
predictive modeling, and executive risk intelligence.

36+30%15–25%
DegreesCore DomainsReporting TAT CutEfficiency Lift

Profile & Expertise

An applied informatician working in Credit Risk

The work combines predictive modeling, statistical analysis, data engineering, and business intelligence to convert
raw lending data into reliable insights improving credit decisions, portfolio performance, and operational outcomes.
It is the foundation that earns the seat at the table, and the domain that keeps the work useful.

Discipline

Applied Informatics applied to Consumer Lending

Domain

Analytics forCredit Risk & Portfolio Management


How I Create Value

Tools follow the problem. The work follows the business.

Each engagement starts with a question the business is actually trying to answer.
The work below is organized around those questions.

Credit Risk Analytics

Frameworks that support underwriting strategy, risk segmentation, and portfolio quality assessment.

  • Underwriting criteria and cut-off optimization

  • Risk segmentation and pricing-tier design

  • Delinquency and portfolio quality monitoring

Portfolio Analytics

Monitoring performance through cohort analysis, delinquency flow, and executive-level KPIs.

  • Vintage and roll-rate analysis

  • Charge-off, recovery, and NPL trend reporting

  • Portfolio-level risk dashboards

Lending Operations Analytics

Improving efficiency across origination, underwriting, servicing, and the borrower lifecycle.

  • Production and approval-funnel analytics

  • Operational KPI and SLA reporting

  • Process automation and cycle-time reduction

Predictive Modeling

Statistical and machine-learning models that anticipate borrower behavior and portfolio risk.

  • Application and behavioral scorecards

  • Probability-of-default and risk-based pricing models

  • Model validation, monitoring, and recalibration

Business Intelligence

Self-service dashboards and reports that give executives and operators a single source of truth.

  • Executive and operational reporting

  • Interactive dashboards in Power BI and Tableau

  • Data storytelling for non-technical audiences

Data Engineering

Scalable ETL pipelines, analytical datasets, and governance that make analytics reliable.

  • ETL and data-pipeline design

  • Data warehousing and quality validation

  • Integration with loan servicing, ERP, and BI layers


Solutions Delivered

Analytical products, not slideware

Each solution below has shipped into a real lending operation,
used by underwriters, risk managers, collections teams, or executive leadership.

Credit Risk IntelligencePredictive analytics and behavioral analysis that support underwriting decisions and ongoing borrower risk assessment. Models aligned to risk appetite, approval targets, and portfolio profitability.

PD / LGD / EAD Scorecards, Risk-Based


Lending Operations AnalyticsPerformance analytics across the loan lifecycle: production metrics, approval pipelines, funding rates, cycle time, and operational efficiency indicators.

Origination Approval Funnel Servicing KPIs


Executive Business IntelligenceSelf-service dashboards delivering trusted metrics for management, operations, risk, and the executive team — consistent definitions, single source of truth.

Power BI, Tableau, Executive Reporting

Portfolio Performance MonitoringInteractive dashboards tracking delinquency, roll rates, vintage performance, charge-offs, recoveries, and portfolio KPIs — from executive summary to cohort deep-dive.

Vintage Roll-Rate NPL / PAR


Predictive Portfolio ModelingMachine learning and statistical models supporting portfolio segmentation, default prediction, early-warning triggers, and risk-based decisioning at the account level.

Classification and Segmentation


Data Integration & Analytics AutomationScalable ETL pipelines integrating loan servicing platforms (NLS), operational databases, ERP systems (LP3), and analytical repositories — with governance and validation baked in.

ETL, NLS · LP3, Azure


Methodology

From business question to data-driven decision

A consistent approach to analytical work, anchored in business context, disciplined in execution, and accountable for the decision it informs.

Business ChallengeThe question the business is actually trying to answer.

Business UnderstandingFrame the problem, define success, identify constraints.

Data AcquisitionIdentify, extract, and consolidate the right data sources.

Validation & GovernanceQuality checks, controls, and auditability from day one.

ETL & Data EngineeringReliable pipelines producing analytical-ready datasets.


Exploratory AnalysisFind the signal: distributions, anomalies, relationships.

Statistical AnalysisInference, hypothesis testing, robust evaluation.

Predictive ModelingScorecards and ML models with validation, KS / Gini / PS

Business IntelligenceDashboards, reports, and self-service for the business.

Executive Decision SupportRecommendations grounded in evidence, tracked through action.

How this reads in practice. A question like "should we adjust the approval cut-off for thin-file applicants in the subprime segment?" moves through every stage: it becomes a measurable problem, a clean dataset, a calibrated model, and finally a recommendation with monitoring built in. The flow is iterative, not linear — but every loop returns to the business question.

Technology Ecosystem

A stack that matches the work

The tools are means, not the message — but the right combination of analytics, BI, data engineering, and domain platforms is what makes the work reliable.

Analytics & Programming

Business Intelligence

Data Engineering

Python: Pandas · NumPy · Scikit-learn · TensorFlow
SQL: SQL Server · PostgreSQL · MySQL · SQLite
MongoDB: Document stores
SAS: Credit risk modeling
SPSS / Minitab: Statistical analysis

Power BI: Executive & operational dashboards
Tableau: Interactive analytics
Excel: Modeling & ad-hoc analysis
Google Sheets: Collaborative reporting

ETL: Pipeline design
Pipelines: Scheduled orchestration
Warehousing: Analytical data marts
Governance: Quality & controls
Validation: Reconciliation & sign-off


Financial Platforms

Analytics Expertise

Nortridge: Loan System (NLS)
LP3: Loan management ERP
Azure: Cloud data & compute

Scorecards: Application · Behavioral · Collections
Vintage: Cohort analysis
KS & Gini: Model discrimination
Forecasting: Loss projection
Feature Eng. Predictor construction

Roll-Rate: Transition matrices
Delinquency PAR · NPL · DPD monitoring
PSI / CSI: Population stability
A/B Testing: Strategy validation
ML: Non-Supervised and Supervised, tree-based models


Business Impact

Analytics should drive outcomes, not just reports

The work below is what "good" looks like when analytics is connected to the operation it serves.

Operational Excellence

Improved operational efficiency through workflow optimization and analytics-driven process improvements across lending and risk operations.


Reduced reporting turnaround by ~30% through automation and standardized reporting solutions.


Delivered efficiency gains of 15–25% by streamlining analytical processes and improving data accessibility for business users.

~30%

Reporting turnaround reduction

Text

Text

Text

Text

Through automation and standardized reporting across credit, portfolio, and operational reporting.

15–25%

Efficiency gains

Text

Text

Text

Text

From streamlined analytical processes and improved data accessibility for business and operational teams.


Text

Credit Risk Management

Enhanced portfolio visibility through integrated monitoring and risk reporting.


Improved underwriting insights using predictive analytics and behavioral analysis.


Supported proactive identification of delinquency and portfolio deterioration trends.

Data & Analytics

Built reliable analytical datasets supporting enterprise reporting and decision support.


Improved data quality through governance and validation practices.


Enabled self-service analytics for business and operational teams across the organization.

6+

Analytical products delivered

Text

Text

Text

Text

From credit risk intelligence to executive BI, integrated data pipelines, and predictive portfolio modeling.


Professional Journey

Roles and companies as evidence, not as the headline

The thread is the evolution of expertise: from data analytics foundations to credit risk specialization, then to risk intelligence and predictive modeling — applied across consumer lending, subprime credit, and auto finance.

  • Foundation

Data Analytics & Business Intelligence

Enterprise systems · Reporting automation · BI platformsBuilt strong foundations in data analysis, enterprise systems, reporting automation, and business intelligence. Established the operational habits — data quality, governance, delivery discipline — that the rest of the work depends on.

  • Specialization I

Consumer Lending Analytics

Loan lifecycle · Underwriting · Operational reportingApplied analytics to optimize loan lifecycle performance, underwriting workflows, operational reporting, and lending efficiency. Built the first working vocabulary of consumer credit — origination, servicing, delinquency, recovery.

  • Specialization II

Credit Risk & Portfolio Analytics

Vintage · Roll-rate · Scorecards · Executive reportingDeveloped portfolio monitoring solutions, delinquency analytics, predictive models, and executive dashboards supporting risk-based decision-making. Scorecards, KS / Gini, PAR / NPL, and transition matrices became daily tools.

  • Where the work is now

Risk Intelligence & Predictive Analytics

ML · Statistical modeling · Portfolio strategyIntegrated applied informatics, machine learning, and statistical modeling to strengthen portfolio management and improve lending strategies. The same quantitative foundation, now applied with more advanced modeling and closer to the strategy conversation.

  • Next

Where this is heading

A team where this combination is exactly the briefThe most useful next role sits at the intersection of credit risk leadership and applied informatics — where the modeling depth and the domain knowledge can be deployed together, not traded off.


Let’s build better decisions with data

Whether it’s improving credit risk strategy, optimizing portfolio performance, automating analytics, or implementing data-driven decision frameworks — I’d be glad to connect.

Areas of Interest

© 2026 Sanchez Vidal W. · Professional portfolio. ·Designed for clarity, accuracy, and signal.

S-VW