Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a Senior Data Scientist and Machine Learning Engineer with 9+ years of experience designing and deploying AI-powered solutions across banking, healthcare, telecom, and retail industries. I specialize in fraud detection, credit risk modeling, customer segmentation, churn prediction, and time-series forecasting, delivering measurable business impact such as reducing risk exposure by 32%, improving retention by 15%, and cutting infrastructure costs by 25%. I thrive in cross-functional environments and enjoy turning complex data into actionable insights that drive strategic outcomes. I have hands-on expertise across Python, R, SQL, and cloud/platform ecosystems (AWS SageMaker, Azure ML). I’ve built end-to-end scalable ML pipelines, NLP solutions, and real-time predictive systems, while emphasizing model governance and regulatory compliance (CCAR, DFAST, Basel III). My work supports enterprise-wide digital transformation, strengthens compliance, optimizes processes, and enhances customer experiences for executive leadership.…I am a Senior Data Scientist and Machine Learning Engineer with 9+ years of experience designing and deploying AI-powered solutions across banking, healthcare, telecom, and retail industries. I specialize in fraud detection, credit risk modeling, customer segmentation, churn prediction, and time-series forecasting, delivering measurable business impact such as reducing risk exposure by 32%, improving retention by 15%, and cutting infrastructure costs by 25%. I thrive in cross-functional environments and enjoy turning complex data into actionable insights that drive strategic outcomes. I have hands-on expertise across Python, R, SQL, and cloud/platform ecosystems (AWS SageMaker, Azure ML). I’ve built end-to-end scalable ML pipelines, NLP solutions, and real-time predictive systems, while emphasizing model governance and regulatory compliance (CCAR, DFAST, Basel III). My work supports enterprise-wide digital transformation, strengthens compliance, optimizes processes, and enhances customer experiences for executive leadership.

Sandeep Reddy Jakkidi

AI Developer, Data Scientist, AI Engineer, +5





I am a Senior Data Scientist and Machine Learning Engineer with 9+ years of experience designing and deploying AI-powered solutions across banking, healthcare, telecom, and retail industries. I specialize in fraud detection, credit risk modeling, customer segmentation, churn prediction, and time-series forecasting, delivering measurable business impact such as reducing risk exposure by 32%, improving retention by 15%, and cutting infrastructure costs by 25%. I thrive in cross-functional environments and enjoy turning complex data into actionable insights that drive strategic outcomes. I have hands-on expertise across Python, R, SQL, and cloud/platform ecosystems (AWS SageMaker, Azure ML). I’ve built end-to-end scalable ML pipelines, NLP solutions, and real-time predictive systems, while emphasizing model governance and regulatory compliance (CCAR, DFAST, Basel III). My work supports enterprise-wide digital transformation, strengthens compliance, optimizes processes, and enhances customer experiences for executive leadership.…I am a Senior Data Scientist and Machine Learning Engineer with 9+ years of experience designing and deploying AI-powered solutions across banking, healthcare, telecom, and retail industries. I specialize in fraud detection, credit risk modeling, customer segmentation, churn prediction, and time-series forecasting, delivering measurable business impact such as reducing risk exposure by 32%, improving retention by 15%, and cutting infrastructure costs by 25%. I thrive in cross-functional environments and enjoy turning complex data into actionable insights that drive strategic outcomes. I have hands-on expertise across Python, R, SQL, and cloud/platform ecosystems (AWS SageMaker, Azure ML). I’ve built end-to-end scalable ML pipelines, NLP solutions, and real-time predictive systems, while emphasizing model governance and regulatory compliance (CCAR, DFAST, Basel III). My work supports enterprise-wide digital transformation, strengthens compliance, optimizes processes, and enhances customer experiences for executive leadership.

Available to hire

I am a Senior Data Scientist and Machine Learning Engineer with 9+ years of experience designing and deploying AI-powered solutions across banking, healthcare, telecom, and retail industries. I specialize in fraud detection, credit risk modeling, customer segmentation, churn prediction, and time-series forecasting, delivering measurable business impact such as reducing risk exposure by 32%, improving retention by 15%, and cutting infrastructure costs by 25%. I thrive in cross-functional environments and enjoy turning complex data into actionable insights that drive strategic outcomes.

I have hands-on expertise across Python, R, SQL, and cloud/platform ecosystems (AWS SageMaker, Azure ML). I’ve built end-to-end scalable ML pipelines, NLP solutions, and real-time predictive systems, while emphasizing model governance and regulatory compliance (CCAR, DFAST, Basel III). My work supports enterprise-wide digital transformation, strengthens compliance, optimizes processes, and enhances customer experiences for executive leadership.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Sr. Data Scientist – Gen AI Developer at Truist Bank

February 1, 2023 - Present

Led development of data science solutions to support fraud detection, credit risk scoring, and customer segmentation initiatives. Built and deployed machine learning models using Python (XGBoost, logistic regression) to identify suspicious activity and reduce false positives in fraud alerts. Collaborated with data engineers to build robust SQL pipelines ingesting daily financial transactions into Redshift and SageMaker. Designed segmentation models using clustering techniques on KYC and behavioral data for personalized product offers. Developed supervised and unsupervised machine learning models reducing financial risk exposure by 32%. Automated regulatory reporting workflows, applied NLP to classify customer feedback, created dashboards in Tableau and Power BI, and developed time series forecasting models for financial metrics. Migrated legacy workflows to AWS platforms and adhered to strict model governance standards.

Data Scientist at UHG

February 1, 2023 - August 26, 2025

Built and maintained advanced machine learning systems focusing on healthcare data analytics and fraud detection. Designed scalable ML systems on Azure, automating data science from research to production. Implemented AWS step functions and orchestrated SageMaker tasks. Deployed ML pipelines for various models using containerized microservices. Developed AI chatbot models integrating LLMs and enhanced ML ecosystem efficiency. Created monitoring frameworks for model performance and bias detection. Automated and orchestrated pipelines using Python, Spark, Hive SQL, MongoDB, and PostgreSQL. Containerized ML models with Docker and Jenkins for CI/CD deployments. Applied advanced NLP and deep learning models leveraging Python, TensorFlow, and BERT.

Data Scientist at Verizon

January 1, 2021 - August 26, 2025

Developed machine learning models for forecasting seasonal demand and customer churn, improving inventory distribution and retention campaigns. Built customer lifetime value models, real-time fraud detection algorithms, and recommendation systems for personalized services. Performed A/B testing to optimize marketing campaigns and analyzed network optimization data. Created ETL workflows and interactive dashboards for reporting customer behavior and network KPIs. Collaborated with marketing and CRM teams to improve acquisition strategies using classification models.

Software Engineer/Python Developer at Ascena Retail Group

December 1, 2019 - August 26, 2025

Designed and enhanced server modules, built customer segmentation and churn prediction models to personalize marketing strategies and improve retention. Analyzed omni-channel sales data, engineered ETL pipelines using Python and SQL, and created real-time dashboards in Tableau and Power BI. Applied NLP for sentiment and product quality analysis from customer feedback. Developed recommendation engines and conducted A/B testing for marketing optimization. Built demand forecasting models to reduce stockouts and excess inventory.

Data Scientist/Machine Learning Engineer at IBM

March 1, 2017 - August 26, 2025

Analyzed mortgage applicant data to identify trends in loan approvals and defaults using Python and R. Performed data imputation and feature engineering to enhance mortgage risk models. Developed machine learning models for credit risk and churn prediction. Applied NLP to analyze customer feedback. Conducted customer behavior analysis and segmentation. Collaborated with data engineers to implement ETL processes and analyzed financial data from Hadoop clusters to optimize loan approval processes. Created rich visualizations with Tableau and Matplotlib.

Sr. Data Scientist – Gen AI Developer at Truist Bank

February 1, 2023 - Present

Led data science initiatives focused on fraud detection, credit risk scoring, and customer segmentation using advanced machine learning models like XGBoost and logistic regression. Developed scalable SQL pipelines for financial data ingestion and deployed models using AWS SageMaker and Redshift. Applied NLP techniques to streamline compliance audits and created dashboards for stakeholder reporting. Migrated legacy workflows to cloud platforms and implemented model governance for regulatory compliance, reducing fraud risk exposure by 32%.

Data Scientist at UHG

February 1, 2023 - August 26, 2025

Designed scalable ML systems on Azure and AWS for fraud detection and healthcare analytics. Automated ML pipelines using Jenkins, Terraform, and Docker with Hugging Face models deployment. Developed healthcare data engineering pipelines using Spark and Hive SQL. Enhanced foundational AI models support including LLMs like ChatGPT for chatbot applications. Implemented monitoring frameworks for model bias and performance. Managed end-to-end ML lifecycle with cloud-native architecture and real-time data processing.

Data Scientist at Verizon

January 1, 2021 - August 26, 2025

Built predictive models for demand forecasting, churn prediction, and customer lifetime value to optimize marketing and retention. Developed real-time fraud detection using anomaly detection and graph analytics. Partnered across teams to analyze network usage and improve UI/UX features. Created ETL workflows and interactive dashboards for executive reporting. Leveraged clustering and recommendation systems to personalize customer offerings effectively.

Software Engineer/Python Developer at Ascena Retail Group

December 1, 2019 - August 26, 2025

Developed customer segmentation and churn prediction models. Engineered ETL pipelines and dashboards for omni-channel retail analytics. Applied NLP on customer feedback for sentiment analysis. Built recommendation engines and implemented A/B testing to optimize campaigns. Collaborated across merchandising and supply chain teams to improve demand forecasting and inventory management.

Data Scientist / Machine Learning Engineer at IBM

March 1, 2017 - August 26, 2025

Analyzed mortgage and credit risk data using Python and R, implementing imputation and feature engineering techniques. Built predictive models for loan approvals and default prediction using ensemble methods and clustering algorithms. Conducted customer behavior analysis and developed recommendation systems. Worked on NLP to analyze customer feedback. Collaborated with data engineering teams to optimize ETL workflows and evaluated models with standard performance metrics.

Sr. Data Scientist – Gen AI Developer at Truist Bank

February 1, 2023 - Present

Developed and deployed fraud detection and credit risk models using Python (XGBoost, Random Forest, Logistic Regression), reducing false positives and overall risk exposure by 32%. Built customer segmentation models (K-Means, DBSCAN) on KYC and transaction data, enabling personalized offers and improving engagement. Automated CCAR and DFAST reporting using SQL and Python, saving 20+ hours weekly. Created NLP pipelines for compliance documents and feedback using BERT and spaCy, cutting audit response times by 40%. Migrated legacy workflows to AWS SageMaker and Redshift, reducing infrastructure costs by 25% and improving reliability. Built ARIMA/Prophet forecasts for deposits, loan prepayments, and market volatility, delivering 20% better accuracy.

Data Scientist at UnitedHealth Group

February 1, 2023 - October 23, 2025

Designed and deployed scalable ML systems for healthcare fraud detection and risk prediction using Azure ML, Python, and Jenkins CI/CD, reducing false positives by 30% and improving fraud identification accuracy. Automated end-to-end ML workflows in AWS SageMaker with Step Functions, boosting pipeline efficiency by 40%. Processed large healthcare datasets with PySpark, Hive SQL, and MongoDB, improving data quality by 25%. Built models including XGBoost, CatBoost, LightGBM, and NLP solutions with BERT/Hugging Face, improving patient outcome predictions by 20%. Implemented monitoring for drift and bias with AWS CloudWatch, ensuring production reliability and regulatory alignment. Collaborated with clinicians, engineers, and data architects to design end-to-end pipelines.

Data Scientist at Verizon

January 1, 2021 - October 23, 2025

Forecasted seasonal demand and optimized inventory across retail stores and e-commerce, improving stock accuracy by 28%. Built predictive churn models (logistic regression, XGBoost, neural networks) reducing churn by 15%. Developed CLV models to prioritize high-value clients, driving 12% more revenue from premium segments. Implemented real-time fraud detection using anomaly detection and graph analytics, reducing false positives and preventing $3M in losses annually. Led A/B and multivariate tests for digital marketing, improving targeting and conversions by 18%. Created dashboards in Tableau/Power BI for leadership insights.

Software Engineer/Python Developer at Ascena Retail Group

December 1, 2019 - October 23, 2025

Designed and developed a scalable server module, resolving critical production issues and reducing downtime by 20%. Built customer segmentation models (K-Means/DBSCAN) to identify high-value groups, boosting engagement and sales by 18%. Designed and deployed predictive churn models to detect at-risk customers, improving repeat retention by 22%. Engineered robust ETL pipelines from Salesforce Commerce Cloud and Oracle Retail, ensuring data quality and 30% reporting accuracy improvements. Created dashboards in Tableau/Power BI to monitor KPIs such as sell-through, markdowns, and online conversions.

Data Scientist / Machine Learning Engineer at IBM

March 1, 2017 - October 23, 2025

Explored mortgage applicant data to identify approval patterns and default risks, improving loan approval accuracy by 18%. Performed data imputation with scikit-learn, enhancing model robustness. Engaged in feature engineering (PCA, normalization, encoding) to boost predictive performance and reduce error by 15%. Built mortgage approval and credit risk models using Python and R. Applied NLP with NLTK to analyze customer feedback, extracting sentiments that improved operational efficiency and customer satisfaction by 25%.

Sr. Data Scientist – Gen AI Developer at Truist Bank

February 1, 2023 - November 25, 2025

Developed and deployed fraud detection and credit risk models using Python (XGBoost, Random Forest, Logistic Regression), reducing false positives and overall financial risk exposure by 32%. Built customer segmentation models with K-Means and DBSCAN on KYC and transaction data to enable personalized offers, increasing engagement and campaign response rates by 27%. Automated CCAR and DFAST reporting workflows using SQL and Python, eliminating repetitive tasks and saving the risk analytics team 20+ hours weekly. Created NLP pipelines for classifying compliance documents and feedback using BERT and spaCy, reducing audit response times by 40% and improving reporting accuracy. Migrated legacy workflows to AWS SageMaker and Redshift, streamlining data ingestion, scaling models, and cutting infrastructure costs by 25%. Built forecasting models (ARIMA, Prophet) for deposits, loan prepayments, and market volatility, delivering 20% better accuracy for treasury management decisions.

Data scientist at UHG

February 1, 2023 - February 1, 2023

Designed and deployed scalable machine learning systems for healthcare fraud detection and risk prediction using Azure ML and Python, effectively reducing false positives by 30% and significantly improving fraud identification accuracy. Automated end-to-end ML workflows in AWS SageMaker with Step Functions to manage data ingestion, model training, and deployment, improving pipeline efficiency by 40%. Processed large healthcare datasets with PySpark, Hive SQL, and MongoDB, performing data cleaning and feature engineering that improved overall data quality by 25% and accelerated model readiness. Built and deployed advanced models (XGBoost, CatBoost, LightGBM) and NLP solutions with BERT/Hugging Face, improving patient outcome predictions by 20%. Developed robust monitoring to track drift, bias, and performance metrics, ensuring production reliability and regulatory alignment.

Data scientist at Verizon

January 1, 2021 - January 1, 2021

Developed and deployed models to forecast seasonal demand and optimize inventory across retail stores and e-commerce platforms, improving stock accuracy by 28% and reducing supply chain inefficiencies. Built predictive churn models to identify at-risk customers, enabling targeted retention campaigns that increased retention rates by 15% across consumer and business accounts. Designed CLV models from billing, usage, and service interactions, driving 12% more revenue from premium segments. Implemented real-time fraud detection using anomaly detection and graph analytics, reducing false positives and preventing $3M in annual losses. Conducted A/B and multivariate tests for digital marketing, boosting targeting accuracy and campaign conversions by 18%. Created dashboards in Tableau and Power BI for executives to monitor customer behavior, network performance, and campaign KPIs.

Data Scientist / Software Engineer at Ascena Retails Group

December 1, 2019 - December 1, 2019

Designed and developed a scalable server module, resolving production issues and reducing downtime by 20% while increasing system stability. Built customer segmentation models using K-Means and DBSCAN to identify high-value groups, enabling targeted marketing that improved engagement and revenue by 18%. Designed and deployed predictive churn models (logistic regression, random forest) to detect at-risk customers, improving repeat retention by 22%. Analyzed omni-channel sales data to inform merchandising and pricing strategies. Engineered robust ETL pipelines using Python and SQL to integrate data from Salesforce Commerce Cloud and Oracle Retail, improving reporting accuracy by 30%. Created interactive dashboards in Tableau and Power BI to monitor KPIs such as sell-through rate and online conversions.

Data Scientist / Machine Learning Engineer at IBM

March 1, 2017 - March 1, 2017

Explored mortgage applicant data to identify approval patterns and default risks, improving loan approval accuracy by 18%. Performed data imputation to handle missing financial data, significantly enhancing model robustness and reducing bias. Engaged in feature engineering (PCA, normalization, encoding) to strengthen predictive performance, reducing error rates by 15%. Built mortgage approval and credit risk models using Python and R, boosting predictive accuracy. Applied NLP techniques with NLTK to analyze customer feedback, extracting sentiment patterns that improved operational efficiency and customer satisfaction by 25%. Developed predictive and ensemble models (Logistic Regression, Random Forest, KNN) for default risk and churn, supporting data-driven decision making.