SVN Rajeswara Reddy
Bangalore
Summary
Accomplished Analytics & Machine Learning Engineering Consultant with 18+ years of experience in Data Engineering, Machine/Deep Learning, GenAI, MLOps, and Software Development across Banking, Retail, and Financial Services domains. Proven expertise in end-to-end ML application development, from model design and optimization to scalable production deployment. Strong background in software design, data pipeline, and cloud-based architectures, ensuring robust, modular, and high-performance ML solutions. Successfully delivered projects for leading clients including IBM, RCI, M&T Bank, Target Corporation, ANZ Bank, Citibank, Aptive, Ollies and Bj’s.
Overview
20
20
years of professional experience
Work History
Analytical Consultant (Offshore Partner)
Bridgetree
12.2019 - 07.2025
- Company Overview: Bridgetree, a U.S.-based data-powered marketing services and technology firm headquartered in Fort Mill, South Carolina
- Served as an offshore analytical consultant for Bridgetree, working directly with client teams. Bridgetree helps brands unify customer data, build smarter segmentation and logic, and execute targeted campaigns across digital and direct channels.
- Delivered advanced analytics solutions (campaign response, look-alike modeling, churn, demand forecasting, fraud detection) to improve targeting and campaign effectiveness.
- Conducted ad-hoc analysis and campaign measurement to evaluate performance, optimize spend, and improve ROI.
- Developed machine learning models in Python and SAS for segmentation, credit scoring, price optimization, and customer engagement.
- Deployed LLM-powered chatbots and Gen AI apps on Snowflake using LangChain and GPT-4, enabling natural language querying, report summarization, and faster business intelligence.
- Partnered with stakeholders to translate data into actionable strategies, driving measurable improvements in revenue and customer experience.
- Designed and deployed advanced ML models (prediction, incremental response, campaign uplift); automated pipelines for training, scoring, and monitoring.
- Applied Python for data science tasks: data import/export (Excel, SQL, flat files), EDA, cleaning, and feature engineering.
- Scoped and executed data science and Gen AI projects (e.g., campaign response prediction, report summarization) with GPT-4, customer advisory copilots using LLaMA 2 + LangChain, clearly defining goals, techniques, and data sources to ensure successful outcomes.
- Clients: Ollies, BJ’s, Academy Sports and Aptive
Technology Specialist
Maveric Systems
10.2017 - 08.2019
- Led the design, development, and deployment of advanced analytical and machine learning solutions to strengthen banking operations across credit risk, fraud detection, customer insights, and regulatory compliance. Designed scalable ML pipelines, automated data workflows, and implemented MLOps practices to ensure production-ready models that enhance decision-making, risk mitigation, and customer engagement. Worked closely with cross-functional stakeholders in risk, compliance, finance, and technology to deliver robust and value-driven banking analytics solutions.
- Model Optimization: Collaborated with risk analysts and data scientists to train, evaluate, and optimize supervised, unsupervised, and deep learning models for accuracy, interpretability, and regulatory compliance.
- Data Engineering for Analytics: Designed and automated ETL/ELT pipelines to process transactional, behavioural, and credit bureau data; implemented feature engineering and data versioning frameworks to support ML workflows.
- MLOps & Established CI/CD for ML models, automated testing, model governance, and monitoring for performance, drift, and bias in production banking systems.
- Performance & Scalability: Resolved system bottlenecks and ensured deployed ML models could scale efficiently under high transaction volumes in banking environments.
- Collaboration: Partnered with risk, finance, and IT teams to integrate ML-driven insights into business processes (credit scoring, fraud alerts, customer retention strategies).
- Research & Innovation: Evaluated new AI/ML techniques (e.g., explainable AI for regulatory reporting) to enhance risk transparency and compliance.
- Documentation: Created comprehensive documentation for data pipelines, ML models, and decision frameworks for audit and compliance purposes.
- Client: CITI BANK
Technical Lead Analyst
Quess Corp
03.2017 - 09.2017
- Led an end-to-end banking analytics project to design, develop, and productionize IFRS 9 provisioning models and related ML solutions. Integrated processes across Risk, Finance, and Accounting to deliver PD, LGD, EAD and Expected Loss calculations (12-month and lifetime) using regression-based techniques and robust data pipelines. Built scalable, auditable model pipelines and MLOps practices so provisioning outputs could feed downstream accounting systems, regulatory reports, and risk dashboards.
- Built Probability of Default (PD), Loss Given Default (LGD), and Exposure at Default (EAD) models using regression, and calculated 12-month and lifetime Expected Credit Loss (ECL) as per IFRS 9 rules.
- PD (Probability of Default): likelihood that a borrower will default.
- LGD (Loss Given Default): how much loss the bank will face if default happens.
- EAD (Exposure at Default): the total value at risk when default occurs.
- Designed ETL pipelines to combine banking, bureau, and macroeconomic data; ensured versioning and traceability.
- Performed backtesting, benchmarking, sensitivity checks; maintained model documentation and audit compliance.
- Automated training, scoring, and monitoring with CI/CD pipelines; set alerts for drift and retraining.
- Produced explainable outputs, dashboards, and automated month-end provisioning reports.
- Worked with Risk, Finance, and IT teams; continuously enhanced models for accuracy, simplicity, and compliance.
- Client: ANZ BANK
Senior Consultant
Capgemini India PVT Ltd
01.2013 - 07.2016
- Designed and implemented a campaign optimization framework for Target Corporation using retail transaction data, demographic data, and past campaign response data. Built classification models to identify the best customers for targeting, improve response rates, and reduce campaign costs.
- Collected and integrated retail transactions, customer demographics, and campaign response data for analysis.
- Performed data preprocessing, feature engineering, and segmentation to prepare inputs for modeling.
- Developed classification models (e.g., logistic regression, decision trees, random forests) to predict customer response likelihood.
- Optimized campaign contact strategy by identifying high-probability responders and excluding low-value segments.
- Measured campaign performance using lift charts, ROC, AUC, and response rate improvement.
- Partnered with Marketing and Business teams to translate model outputs into actionable targeting rules and campaign lists.
- Automated scoring pipelines for ongoing campaigns and built dashboards to track campaign ROI and effectiveness.
- Performed data preprocessing, including missing value treatment, outlier handling, and data normalization.
- Applied feature engineering techniques such as variable transformation, categorical encoding (one-hot, label, WoE), and binning (supervised/unsupervised) for predictive modeling.
- Performed model validation using cross-validation, stability checks, and multicollinearity diagnostics.
- Client: Target Corporation
Assistant Manager
WNS Global Services
08.2008 - 07.2012
- The project supports the Retail Deposits business team at M&T Bank by managing and enhancing bill payments data processing. The goal is to ensure accurate, timely, and efficient handling of deposits-related payment transactions, improve reporting for M&T Bank’s retail banking operations, and support compliance with regulatory requirements.
- Partnered with the Retail Deposits business team at M&T Bank to understand bill payments requirements and transaction processing rules.
- Designed and developed SAS ETL processes to extract, transform, and load M&T Bank’s retail deposits and bill payments data from multiple banking systems.
- Automated reconciliation of deposit transactions and bill payments using SAS procedures to minimize operational errors.
- Built SAS-based reports and dashboards for M&T Bank to monitor deposit inflows/outflows, transaction failures, and SLA adherence.
- Created reusable SAS macros to streamline repetitive tasks and enhance processing efficiency for M&T Bank’s retail deposits operations.
- Conducted data quality checks and exception reporting to ensure clean, reliable deposit data for M&T Bank’s decision-making.
- Performed ad-hoc analysis in SAS to provide insights into retail deposit trends, customer bill payment behaviors, and exception handling.
- Implemented performance tuning in SAS for handling large volumes of deposit and payment transactions at M&T Bank efficiently.
- Coordinated with Finance, Risk, and Compliance teams at M&T Bank to ensure SAS processes adhered to banking regulations and audit requirements.
- Supported SIT/UAT testing and production deployment of enhancements in the M&T Bank retail deposits bill payments system.
- Provided production support for SAS jobs at M&T Bank, ensuring timely processing of deposit transactions and quick resolution of issues.
- Client: M&T Bank
Software Consultant
Marketics Technologies
10.2005 - 07.2008
- Developed and implemented a reporting and analytics solution for RCI, a leading U.S. resort exchange vacation provider. RCI runs exchange vacation programs that allow members to discover new destinations and redeem points for vacations and travel-related products, including airfare, cruises, car rentals, and hotel reservations. The reporting system consolidated data from membership databases, booking systems, and partner integrations to provide a 360 view of customer activity, points redemption, and partner service adoption. The solution enabled data-driven decision-making, improved customer engagement strategies, and optimized loyalty program management.
- Getting Data from Data source to create SAS Datasets
- Collaborated with business stakeholders to gather reporting and analytics requirements.
- Developed interactive dashboards and reports to track customer behavior, program performance, and revenue trends.
- Automated reporting workflows to reduce manual effort and improve data accuracy.
- Created ad-hoc and scheduled reports for marketing, finance, and operations teams.
- Ensured data quality, consistency, and governance across reporting layers.
- Worked closely with leadership to provide insights on customer engagement and program optimization.
- Tools & Technologies: SQL, SAS, Excel and ETL tools
- Client: RCI
Software Consultant
Marketics Technologies
10.2005 - 07.2008
- Developed a Propensity-to-Buy (PTB) classification machine learning model for IBM’s product portfolio to segment customers and non-customers based on their likelihood to purchase IT products and solutions. The project leveraged IBM’s client tiering framework, applying the 80/20 rule on revenue and Total Served Opportunity (TSO) to identify high-value customers and focus areas for growth. By integrating structured data (transaction history, customer demographics, firmographics, and product usage) with unstructured data (customer interactions, campaign responses), the model provided actionable insights to the sales and marketing teams. The solution enabled customer prioritization, targeted campaigns, improved conversion rates, and increased revenue efficiency.
- Collaborated with IBM stakeholders to understand client tiering and product segmentation.
- Collected and integrated datasets from CRM systems, sales databases, and external sources.
- Performed data cleaning, feature engineering, and exploratory data analysis (EDA) to identify purchase indicators.
- Built classification models (Logistic Regression, Random Forest, Gradient Boosting) to predict purchase propensity.
- Applied feature selection techniques to enhance model interpretability and performance.
- Tuned hyperparameters and validated models using cross-validation.
- Assessed models using AUC, ROC, precision, recall, and lift charts.
- Identified top drivers influencing purchase decisions and provided business-friendly insights.
- Created a customer scoring framework to rank customers by their likelihood to buy.
- Implemented the model into IBM’s sales and marketing workflows for real-time scoring.
- Automated reporting dashboards to track performance and campaign ROI.
- Supported sales teams with segmentation strategies to optimize resource allocation.
- Used SAS, SQL and MS Excel for reporting, analytics, and visualization.
- Client: IBM
Education
MCA -
Bangalore University
01.2003
B.Sc - Statistics and computers
Osmania University
01.2000
Skills
- Python (Pandas, NumPy, Scikit-learn, PyTorch, TensorFlow, Streamlit, FastAPI)
- SQL (MySQL, Oracle, SQL Server, PostgreSQL, HiveQL, SparkSQL, BigQuery)
- SAS
- Visualization: Tableau, Power BI, MS Excel, TheBricks
- Cloud & Data Platforms: AWS (S3, Redshift, SageMaker), Azure (Data Lake, Synapse), GCP (BigQuery, Vertex AI), Snowflake
Timeline
Analytical Consultant (Offshore Partner)
Bridgetree
12.2019 - 07.2025
Technology Specialist
Maveric Systems
10.2017 - 08.2019
Technical Lead Analyst
Quess Corp
03.2017 - 09.2017
Senior Consultant
Capgemini India PVT Ltd
01.2013 - 07.2016
Assistant Manager
WNS Global Services
08.2008 - 07.2012
Software Consultant
Marketics Technologies
10.2005 - 07.2008
Software Consultant
Marketics Technologies
10.2005 - 07.2008
B.Sc - Statistics and computers
Osmania University
MCA -
Bangalore University
Similar Profiles
Anil PurswaniAnil Purswani
Enterprise Application Manager at BridgetreeEnterprise Application Manager at Bridgetree
Karen SellKaren Sell
Senior Campaign Engineer at Bridgetree LLCSenior Campaign Engineer at Bridgetree LLC
Simran SSimran S
Travel Consultant at BCD TravelTravel Consultant at BCD Travel
Kannan LKannan L
Service Owner - Identity Global Products at AXA Global Business ServicesService Owner - Identity Global Products at AXA Global Business Services
Sheetal K SSheetal K S
Salesforce QA at PwC AdvisorySalesforce QA at PwC Advisory