What is a Lead Data Scientist?

A Lead Data Scientist owns data science strategy and delivery for a product or domain: defining problems, designing experiments and models, partnering with engineering on production systems, and mentoring others. At senior levels they also shape roadmaps, technical standards, and cross-team alignment for ML and analytics at scale.

What is Reinforcement Learning?

Reinforcement Learning (RL) is a machine learning paradigm where an agent learns to make decisions by interacting with an environment, receiving rewards or penalties. It's used in recommendation systems, game playing, robotics, and personalized systems. Common RL techniques include multi-armed bandits, contextual bandits, and deep Q-networks (DQN).

What is GenAI and RAG?

Generative AI (GenAI) refers to AI systems that can generate new content. RAG (Retrieval-Augmented Generation) combines information retrieval with language models to provide accurate, context-aware responses. RAG systems are used in chatbots, search systems, and automated workflows.

What are Multi-Arm Bandits?

Multi-Arm Bandits are a class of reinforcement learning algorithms that balance exploration (trying new options) and exploitation (using known best options). They're widely used in recommendation systems, A/B testing, and personalized systems to optimize user engagement and business metrics.

Utsav Mishra

Lead Data Scientist with 8+ years of experience building machine learning, reinforcement learning, and GenAI systems, including patented solutions delivering over $500M in business impact at Target.

Lead Data Scientist

About Me

I’m a Lead Data Scientist with 8+ years shipping ML, reinforcement learning, and GenAI in production—mostly in retail and fintech—across recommendation, personalization, and decision systems at scale.

As Lead Data Scientist (L6) at Target, I lead offer personalization and related data science: technical strategy for platforms used by 100M+ guests, mentoring a large DS/engineering org, and work that includes patented RL-based systems and GenAI tooling with measurable revenue impact.

Key Expertise Areas

Reinforcement Learning & Multi-Arm Bandits: Contextual bandits, DDQN, and exploration–exploitation strategies for large-scale recommendation systems
Generative AI & RAG Systems: Production RAG systems for automated forecasting, intelligent retrieval, and decision support
Deep Learning: LSTM, CNN, and neural architectures for time-series forecasting and computer vision
MLOps & Cloud Infrastructure: Scalable ML pipelines on GCP and AWS using Kubeflow, Spark, and TensorFlow
Causal ML & Experimentation: Robust A/B testing frameworks and causal inference for data-driven decisions

Notable Achievements

Patented Innovation: Invented Target’s Contextual Offer Recommendation Engine (CORE), generating $500M+ incremental sales
Team Leadership: Lead teams of 16+ data scientists and engineers; mentored 5+ team members to promotions
Industry Recognition: VP Award for Innovation & Impact; featured on Target Tech Blog
Scale: Architected systems serving 100M+ users with real-time personalization

Want to learn more? Check out my portfolio, view my resume, or get in touch!

View Portfolio Learn More Contact Me

Work Experience

Lead Data Scientist (L6), Target Corporation

October 2021 —

• Architected and owned the ML strategy and technical roadmap for Target's offer personalization platform (100M+ users), defining experimentation frameworks, model architectures, and scaling patterns for multi-market deployment.
• Drove technical architecture decisions across a team of 16 data scientists and engineers, establishing best practices for model design, MLOps pipelines, and cross-team ML integration.
• Mentored and grew 5 data science team members, coaching on advanced ML techniques and research-to-production translation; two received promotions.
• Invented & patented Target's Contextual Offer Recommendation Engine (CORE), an RL-based contextual bandit framework. Architected the system from research to production, driving +70% redemption and +28% opt-in uplift (stat-sig), contributing over $500M incremental sales.
• Designed and led development of TargetRun, a guest-level trip forecasting system using LSTM that achieved statistically significant improvements, reducing MAPE and MAE by ~50% and driving measurable lifts in campaign opt-in, completion, and redemption rates across all engagement segments.
• Designed and led development of Lookalike, a GenAI-powered RAG system that automates campaign forecasting through intelligent retrieval and ranking, achieving 100% coverage (K=3 recommendations), eliminating manual campaign triage.
• Architected automated ML data and training pipelines on GCP using Spark, Kubeflow, and Oozie with TensorFlow Agents; established standardized model tracking and monitoring through TensorBoard and Grafana.
• Technical thought leadership: Presented advanced ML methodologies at company-wide technical forums and received VP Award for Innovation & Impact.

Applied Data Scientist 2, Tata AIA Life

April 2020 — October 2021

• Applied NLP techniques including Gensim LDA topic modeling to identify drop-off points in customer onboarding, achieving 6.2% conversion rate increase. Developed interactive journey visualizations using Plotly Sankey diagrams.
• Developed a GBM regression profit prediction model (R² = 0.991) and deployed it in production via FastAPI; reduced valuation TAT by 30 days. Implemented SHAP for feature attribution and built Streamlit visualization for explainable AI.

Machine Learning Engineer, HDFC Life

January 2018 — March 2020

• Developed a Face Recognition system with Anti-Spoofing capabilities using CNN and DeepFace embeddings to reduce fraud in virtual customer onboarding. Deployed as a containerized service using Docker and ECS.
• Designed and developed the serverless architecture of Lead allocation and Route optimisation app on AWS Data Lake (Lambda, DMS, Dynamodb, Step Function, S3, API Gateway, and Docker).
• Built a cost-sensitive Medical Risk classification model using Deep Reinforcement Learning (DDQN), achieving >91% accuracy while intelligently balancing diagnostic test costs.

Education

Indian Institute of Technology, Kharagpur

B.Arch Honours, ARP

July 2014 — April 2019

Relevant Coursework : Programming & Data Structures, Probability - Mathematics 1 & 2, Image Processing & Remote Sensing, Economics Micro & Macro.
Extracurricular : Sponsorship Head Spring Fest, Web Head SSAP ARP, Lead National Service Scheme Unit - 5.
Recipient of Merit Cum Means Scholarship provided by the Government of India for Academic excellence.

Kendriya Vidyalaya, Andrews Ganj

Science PCM C++

April 2010 — April 2013

Percentage : 88.7% in XII (AIISCE).
Cum GPA : 9.8 in X (AISSE-CBSE)
Received Merit Certificate from CBSE for prolific academic performance in AISSE &AISSCE in 2011 & 2013.