ANURAAG THAREJA
Gurugram
Summary
Results-driven Data Science and Machine Learning professional with 9 years of experience in financial services, retail lending, and consumer analytics. Expertise in Python, SQL, PySpark, and predictive analytics, encompassing the full project lifecycle from problem definition to model deployment. Experience with LLMs, RAG, and GenAI architecture, effectively translating technical insights into impactful business strategies.
Overview
1
1
Certification
12
12
years of professional experience
Work History
Senior Data Analyst / Data Scientist
INCEDO INC.
Gurugram
11.2024 - Current
- Partner with Data Science and Data Engineering teams to validate machine-learning outputs, assess data quality and integrate model outputs into existing production pipelines.
- Integrate alternative and internal data sources into pipelines supporting purchase propensity and customer targeting models, contributing to approximately 25% improvement in targeting/model accuracy.
- Perform large-scale data analysis, preprocessing and feature engineering across income, debt, property taxes, property value, equity, income status, home tenure and related financial attributes.
- Engineered scalable Python, PySpark, and SQL pipelines for mortgage and home-equity customer qualification, lead generation, retention, and cross-sell initiatives, enhancing data accessibility and usability.
- Develop and optimize PySpark and Spark SQL pipelines, delivering approximately 80% improvement in data-processing efficiency across relevant workloads.
- Translated lending business requirements into scalable data-driven qualification and decisioning rules, developing and validating home-equity signals such as Fixed Rate Lock, Emergency Funds, Maturity, Line Utilisation, and Other Purposes, improving decision-making accuracy.
- Collaborated with Data Engineering to ensure production readiness, testing, issue resolution, code reviews, and releases in Agile/Scrum teams using Jira and Git, streamlining deployment processes.
Assistant Manager – Analytics
WNS GLOBAL SERVICES
Gurugram
05.2021 - 11.2022
- Developed time-series forecasting solutions for revenue and business planning using predictive techniques to identify trends and support decision-making.
- Delivered analytics for consumer products and retail revenue workstreams, translating business objectives into analytical frameworks that informed strategic decision-making.
- Developed KPI dashboards and reporting solutions using Power BI, contributing to approximately 30% improvement in reporting efficiency.
- Built data-processing workflows using Python, SQL and Excel for restructuring, transformation, and quality validation of analytical datasets, enhancing data integrity for analysis.
- Applied NLP techniques to consumer purchasing behaviour, uncovering patterns that provided actionable customer insights for targeted marketing strategies.
- Developed an IRP / iLSO proof-of-concept optimization solution and supported data governance and quality-control processes.
- Worked with business stakeholders to translate commercial problems into data science problems and communicate findings to non-technical audiences.
Senior Training Consultant
CROMA CAMPUS
Noida
02.2020 - 08.2020
- Delivered training programmes in Data Science, Python, SQL, and Tableau through structured workshops, achieving measurable learner outcomes.
Data Analyst
SHERYL STRATEGIC SOLUTIONS PVT LTD
Noida
09.2016 - 01.2020
- Managed the full model lifecycle for credit risk scoring models — including PD modelling, validation, deployment, and governance documentation aligned with Model Risk Management principles — reducing loan and credit card default rates by 12%.
- Engineered features and modelled behavioural and transactional datasets similar to Open Banking data, extracting predictive financial signals for credit risk scoring and customer behavioural analytics, enhancing analytical capabilities.
- Authored comprehensive model documentation for governance review — detailing model assumptions, validation methodology, performance benchmarking, and bias assessment — solidifying Model Risk Management.
- Collaborated as core Agile team member across data engineering, product, and risk functions to deliver data-driven financial solutions, contributing to effective project outcomes.
Software Developer
NIIT TECHNOLOGIES (NOW COFORGE)
Greater Noida
07.2014 - 06.2016
- Developed and maintained COBOL code on IBM mainframes to support core banking applications across full SDLC — requirements, development, testing, integration.
- Enhanced IT service delivery by implementing ServiceNow and adopting ITIL best practices.
Education
PGDM - Data Science
Indian Institute of Management Calcutta
01-2019
B.Tech - Computer Science
Lingayas University
01-2013
Skills
- Programming & Data: Python, SQL, PySpark, Spark SQL, Pandas, NumPy, Data processing, EDA, ETL/ELT
- Machine Learning: Scikit-learn, Classification, Regression, Propensity analysis, Feature extraction, Model evaluation, Forecasting
- Deep Learning / NLP: NLP, BERT, RNN, LSTM, Transformer Architectures, Text Representation, Sequence Modelling
- GenAI: LLMs, RAG, Embeddings, Semantic Search, LangChain, Prompt Engineering, Structured LLM Outputs
- Cloud / Engineering: AWS, GCP, Apache Spark, Git, FastAPI, Data pipeline production, Code Reviews
- Analytics: Power BI, Tableau, Plotly, Excel
- Business data translation
- Cross-team collaboration
- Stakeholder Management
- Agile Jira Confluence Alation
AI PROJECT
AI-POWERED RECRUITMENT PLATFORM
- AI Recruitment Automation
- LLM Architecture
- RAG Workflows
- Hybrid Retrieval
- Prompt Engineering
- PDF Extraction
- Structured Outputs
- BERT / RNN / LSTM
- FastAPI Prototype
- Semantic Matching
- Metadata Filtering
- Scalable AI Services
- 80% Effort Reduction
Certification
- Facial Expression Recognition with Keras — Coursera
- Credit Risk Modeling — Udemy
- Market Research Foundations — LinkedIn Learning
- Generative AI / LLM Application Development, RAG & Vector Search - Coursera, Udemy, Scaler and reverse engineered hands-on independent learning
Timeline
Senior Data Analyst / Data Scientist
INCEDO INC.
11.2024 - Current
Assistant Manager – Analytics
WNS GLOBAL SERVICES
05.2021 - 11.2022
Senior Training Consultant
CROMA CAMPUS
02.2020 - 08.2020
Data Analyst
SHERYL STRATEGIC SOLUTIONS PVT LTD
09.2016 - 01.2020
Software Developer
NIIT TECHNOLOGIES (NOW COFORGE)
07.2014 - 06.2016
PGDM - Data Science
Indian Institute of Management Calcutta
B.Tech - Computer Science
Lingayas University