Sai Krishna Suraparaju

Senior Data Analyst with over 11 years of experience in Insurance Data Analytics, specializing in claims Analysis and operational data optimization. Proficient in Python, Power BI, and Tableau, leveraging these tools to enhance process automation and improve data accuracy. Demonstrates strong leadership by mentoring teams and driving strategic insights for business improvement, aiming to innovate and streamline data processes in the insurance sector.

• Collected, cleaned, and analyzed large datasets from claims processing, policy servicing, and retirement services operations to identify patterns, anomalies, and opportunities for process improvement.
• Designed and maintained Power BI dashboards to track claim settlement times, policy changes, and operational KPIs, enabling leadership to make data-driven decisions.
• Automated repetitive reporting tasks using Python and Excel macros, reducing manual effort and improving turnaround time for claim status updates, maturity settlements, and withdrawals.
• Conducted trend analysis on Income Settlements, Maturities, and Contract Changes to forecast workloads, detect policy risk factors, and optimize resource allocation.
• Developed reconciliation reports for premium payments, fund transfers, and withdrawals, ensuring 100% financial accuracy across Group, Whole Life, and Individual policies.
• Created ad-hoc analytical reports for Direct Deposits, Death Claims setup, Ownership changes, Beneficiary updates, and Spousal changes to ensure compliance with internal guidelines and regulatory standards.
• Performed variance and root cause analysis for claim delays and escalations, implementing corrective actions to reduce SLA breaches.
• Applied statistical methods to measure the effectiveness of process changes in reducing claim processing times and improving accuracy.
• Partnered with compliance teams to monitor KYC/AML checks through data-driven risk scoring and anomaly detection.
• Delivered actionable insights on Retirement Services operations (Loan payments, Cash items, Rollovers, Slash E’s, Money-In, Systematic withdrawals, Partial/Full withdrawals) by evaluating transaction patterns and identifying inefficiencies.
• Built predictive models to detect potential fraudulent claims and suspicious financial transactions before payout.
• Provided senior management with weekly and monthly data decks summarizing key operational trends, SLA adherence, and improvement opportunities.
• Mentored junior analysts on using data visualization, SQL querying, and Python scripts for claims analytics and process optimization.

• Objective: Predict inventory shortages and enable proactive supply chain interventions. Methods & Tools: Random Forest, XGBoost, Feature Engineering for class imbalance. Data: 200k+ records. Results: Achieved high recall and precision, delivering SKU-level monitoring and procurement recommendations.

• Objective: Evaluate financial, operational, and cybersecurity risks in blockchain currency platforms. Methods & Tools: Compliance scoring models, threat modeling, risk evaluation frameworks. Impact: Identified vulnerabilities linked to market volatility and cyberattacks. Presented mitigation strategies that enhanced security posture and regulatory compliance.

• Objective: Forecast stock price trends for strategic decision-making. Methods & Tools: Holt-Winters, Decomposition, Regression Models; Power BI for visualization. Analysis: Studied trend, seasonality, and volatility drivers. Results: Selected best-fit model using RMSE, MAPE, and R² performance metrics.

• Objective: Detect high-risk life insurance policies and uncover claim inconsistencies. Methods & Tools: SQL workflows, root cause analysis, fraud detection indicators. Impact: Revealed error patterns, improved compliance collaboration, and reduced policy-level errors.

• Objective: Assess enterprise-level risks for Facebook’s Diem cryptocurrency. Methods & Tools: Likelihood-Impact scoring, Risk Mapping, compliance assessment. Key Actions: Prioritized mitigation strategies and proposed technical security improvements for blockchain validation.

• Objective: Anticipate market and business trends for informed planning. Methods & Tools: Multiple Regression, Holt-Winters, Decomposition; Power BI dashboards. Analysis: Detected seasonal and cyclical patterns in historical data. Impact: Enabled management to anticipate and respond to market changes effectively.