ADITYA RANJAN

Data Scientist | Quantitative Analyst

Pune, IN.

About

Results-driven Data Scientist with 3+ years of experience in developing analytical solutions, statistical models, and risk quantification frameworks within banking and financial services. Expert in leveraging Python, SQL, and advanced statistical methods to derive actionable insights from complex financial datasets, specializing in predictive modeling, financial risk analysis, and data-driven decision-making. Eager to contribute to analytics-led initiatives in Data Scientist or Quantitative Analyst roles within fintech and risk management.

Work

Deutsche Bank / DWS via Infosys Ltd.

|

Data Analyst – Portfolio Analytics & Risk Quantification

Pune, Maharashtra, India

→

Summary

Currently supporting portfolio risk analytics and regulatory reporting for Deutsche Bank/DWS, leveraging Python and statistical models to quantify market risk and inform strategic decisions.

Highlights

Supported portfolio risk analytics framework using Python (Pandas, NumPy) to quantify market risk exposures across 500+ securities, contributing to daily VaR reports for senior management and regulatory reporting.

Utilized statistical models to assess portfolio concentration risk, correlation matrices, and stress-test scenarios, identifying anomalies to inform portfolio rebalancing decisions.

Conducted variance analysis on historical portfolio performance vs. predicted models, validating model accuracy and informing strategy adjustments.

Worked with risk and compliance teams using statistical methods to quantify operational risks and support control enhancements.

Citi Bank via Infosys Ltd.

|

Data Analyst – Process Automation Analytics & Feasibility Modeling

Pune, Maharashtra, India

→

Summary

Conducted quantitative feasibility and impact analysis for process automation initiatives at Citi Bank, leveraging predictive modeling and statistical methods to optimize ROI and project accuracy.

Highlights

Supported quantitative feasibility analysis on 80-100 data points per automation process, applying statistical scoring models to assess automation ROI and implementation priority.

Developed predictive models to estimate effort, cost, and timeline for automation solutions, improving project estimation accuracy by 25%.

Assisted in process mining and statistical analysis of operational workflows, quantifying efficiency gains (time savings, error reduction, cost impact) from Xceptor automation implementations.

Collaborated on Analytical Requirements Documentation (ARD), translating business metrics and statistical findings into technical specifications and securing stakeholder approval within 2 weeks.

Executed testing of automation solutions using statistical sampling and validation protocols, achieving 99% accuracy and confidence levels before production deployment.

Developed analytical dashboards to track automation KPIs (processing time, accuracy rates, cost savings), supporting ongoing performance measurement.

Truist Bank via Infosys Ltd.

|

Data Analyst – Financial Data Analytics & Client Profitability Modeling

Pune, Maharashtra, India

→

Summary

Analyzed client profitability data and financial transactions for Truist Bank, developing statistical models and data validation pipelines to drive data-driven business decisions.

Highlights

Developed statistical models to analyze client profitability across 15+ Corporate & Investment Banking (CIB) clients, decomposing revenue drivers and cost attribution via regression analysis.

Performed exploratory data analysis (EDA) on 100K+ records from Microsoft Exchange and financial transaction datasets, identifying patterns in client behavior and revenue concentration risks.

Assisted in designing and implementing data validation pipelines using SQL and Python, reducing manual errors.

Conducted hypothesis testing on monthly profitability variations to distinguish statistically significant trends, assisting in data-driven business decisions.

Supported customer segmentation using clustering techniques to identify high-value vs. high-risk client profiles, informing pricing and service strategies.

Assisted in database statistical validation during corporate product restatements and Mergers of Equal events, supporting data integrity through chi-square tests and distribution analysis.

L&T Infotech

|

Data Engineering Analyst – Economic Data Modeling & Validation

Chennai, Tamil Nadu, India

→

Summary

Supported data modeling and validation for economic forecasting at L&T Infotech, ensuring statistical accuracy and robustness of econometric formulas for 12+ major industries.

Highlights

Supported the data modeling team in validating complex econometric formulas across 12+ major industries, ensuring statistical accuracy and model robustness for economic forecasting.

Performed data quality audits using SQL and statistical tests to identify missing values, outliers, and data inconsistencies in large economic datasets.

Structured data pipelines using Python (Pandas) and SQL to extract, transform, and validate economic data for the Ministry of Statistics & Programme Implementation (MoSPI).

Supported analytical documentation, explaining data lineage, transformation logic, and statistical assumptions for downstream analytical teams.

Collaborated with quantitative economists to optimize data structures for econometric analysis and time series modeling.

Education

Madras School of Economics

Chennai, Tamil Nadu, India
→
Post Graduate Diploma Masters in Research and Business Analytics Grade: 7.63 / 10.0

Courses

Machine Learning

Econometrics

Statistics & Probability

Derivatives and Options Pricing

Credit Risk Analysis

Financial Modeling

St. Xavier's College

Ranchi, Jharkhand, India
→
Bachelor Bachelors in Economics (Honors) Grade: 63.54%

Certificates

Xceptor Core Configuration: Foundation Certification

Xceptor

Skills

Programming Languages

Python (Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn, Plotly), SQL.

Machine Learning

Regression, Classification, Clustering, Decision Trees, Random Forests, PCA, Neural Networks, Predictive Modeling, Time Series Analysis.

Statistical Methods

Econometrics, Hypothesis Testing, A/B Testing, Probability Distributions, Correlation Analysis, ANOVA, Linear/Logistic Regression, Statistical Modeling, Exploratory Data Analysis (EDA), Monte Carlo Simulation.

Financial Modeling & Risk Management

VaR Calculation (Parametric, Historical, Monte Carlo), Derivatives Pricing, Options Valuation, Cross-Hedge Strategy, Portfolio Analytics, Risk Quantification, Market Risk Analysis, Credit Risk Assessment, Operational Risk, Value-at-Risk (VaR), Volatility Modeling.

Data Visualization

Power BI, Matplotlib, Seaborn, Plotly, MS Excel (Advanced).

Databases & ETL

SQL (Joins, Aggregations).

Tools & Platforms

Git/GitHub, Jupyter Notebook, LaTeX, Confluence, ServiceNow, JIRA, MS Office Suite.

Interests

Sports

Badminton.

Community

Hackathon Participant.

Innovation

Social Science Exhibition Contributor.

Projects

Financial Risk Quantification – Value-at-Risk (VaR) Analysis

→

Summary

Developed and validated a comprehensive Value-at-Risk (VaR) model to quantify market risk across equity portfolios, demonstrating applied statistical risk quantification relevant to portfolio management and regulatory compliance (Basel III).

Housing Price Prediction using Machine Learning

→

Summary

Engineered an end-to-end machine learning pipeline for housing price prediction, demonstrating statistical rigor from data cleaning to model evaluation and deployment.

Image Classification using Deep Learning – Python Implementation

→

Summary

Implemented and evaluated multiple deep learning classification models on image datasets, demonstrating expertise in ML algorithms, statistical validation methods, and Python-based model development.

Cross-Hedge Strategy for Commodity Price Risk Mitigation

→

Summary

Designed and backtested a cross-hedge strategy using correlation analysis and beta calculations to mitigate price risk in commodity futures contracts, demonstrating application of financial risk management and quantitative analysis to real-world derivatives and hedging scenarios.

Empirical Study: Financial Inclusion Index for India

→

Summary

Developed a multi-dimensional financial inclusion index for India using econometric modeling and statistical aggregation techniques, translating statistical findings into actionable policy insights for central banking and financial development initiatives.