AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Lead Data Scientist | GenAI (LLMs) | Machine Learning | Real Estate & Retail | Customer Analytics, Risk Modeling & Predictive Intelligence | IIT Kanpur | 3AI ZENITH Spotlight Award Winner | Mentor
I’m a Lead Data Scientist with 10+ years of experience (M.Tech, IIT Kanpur) building AI/ML and Generative AI solutions that solve real business problems across real estate, retail, and customer analytics domains. Over the last few years, I’ve been particularly focused on applying Generative AI and LLMs to enterprise use cases — from auto-classification and narrative generation to operational intelligence and decision support systems. One of the recent solutions I worked on achieved ~96% accuracy on unseen data while reducing manual operational effort from approximately one week to a few hours. What I enjoy most is combining strong technical problem-solving with business understanding — whether it’s improving customer engagement, predicting churn, building risk scoring frameworks, or helping leadership teams make faster and better decisions using data. My experience spans the full AI/ML lifecycle: • Problem framing & stakeholder discussions • Data engineering & feature engineering • Machine learning & predictive modeling • Generative AI / LLM applications • Model deployment & monitoring • Driving adoption of AI solutions across business teams Technically, I work across: • Generative AI & LLMs (classification, summarization, narrative generation, prompt engineering) • Machine Learning & Predictive Modeling (XGBoost, Random Forest, forecasting, churn/risk models) • Customer Analytics (engagement scoring, segmentation, behavioral analytics) • Python, SQL, Azure OpenAI, Databricks, Docker, Streamlit, Flask I’ve also worked closely with business stakeholders, internal teams, and external vendors on requirement gathering, solution evaluation, and enterprise AI initiatives. Passionate about building scalable AI solutions that create measurable business impact. Currently open to opportunities in Data Science, AI, and Generative A
Indian Institute of Technology, Kanpur
Master’s Degree, Data Science
January 1, 2015 – January 1, 2017
Maharana Pratap University of Agriculture and Technology
Bachelor of Technology (B.Tech.), Electronics and communication Engineering
January 1, 2011 – January 1, 2015
MDS Public School,Udaipur
High School
January 1, 2009 – January 1, 2011
St. Gregorios Sr. Sec. school
SSC
January 1, 2003 – January 1, 2009
ALDAR
Senior Associate - Data Scientist
June 1, 2022 – Present
United Arab Emirates
Swvl
Product Data Scientist
January 1, 2022 – May 1, 2022
Dubai, United Arab Emirates
Anheuser-Busch InBev
Senior Data Scientist - Analytics
November 1, 2021 – December 1, 2021
Bengaluru, Karnataka, India
Analytics India Magazine
Data Science Mentor
July 1, 2020 – August 1, 2021
Ericsson
Data Scientist
October 1, 2018 – November 1, 2021
Bengaluru, Karnataka, India
CoreCompete LLC
Associate Data Scientist
July 1, 2017 – September 1, 2018
Greater Hyderabad Area
CoreCompete LLC
Data Science Intern
May 1, 2016 – July 1, 2016
Hyderabad, Telangana, India
Indian Institute of Technology, Kanpur
DPC, IME M.Tech
April 1, 2016 – March 1, 2017
Airports Authority of India
Intern
June 1, 2014 – July 1, 2014
Udaipur
ETL Development for Global Auto Parts Retailer
August 1, 2017 – September 1, 2018
US Based retail client operates with more than 3000 stores carrying millions of products across US. - Migrate Oracle SQL to pySpark to reduce the processing time required to create the Prediction Input Abstract base table, which is the input for demand forecasts, assortments and replenishment forecasts - Coordinate with Business team to translate different requirements to automated processes which requires data analysis and end-to-end technical implementation on the AWS platform - Loading the output data of different process into PostGres Database for easy utilization by end user Tools: pySpark, HiveQL, SQL, Shell scripting, Sqoop
Development of a Money Attitude and Financial Behavior Scale for Indians [M. Tech Thesis]
October 1, 2016 – May 1, 2017
- Developed a 36 questions questionnaire in English and Hindi and gathered data from 625 respondents scattered across 20 villages and 22 cities across India using online surveys as well as personal interviews. - Exploratory factor analysis yielded 6 factors which were named (i) ‘Financial Prudence’, (ii) ‘Extravagance’ (iii) ‘Financial Knowledge’, (iv) ‘Financial Anxiety’, (v) ‘Importance Attached to Money’ and (vi) ‘Financial Support Network’. - After obtaining the 6-factor model with eighteen items, confirmatory factor analysis of this model was conducted with the sample of individuals who had been administered with the Hindi questionnaire.
Customer Churn Prediction and Segmentation using Python
May 1, 2016 – July 1, 2016
• Worked with a large dataset from the telecommunication sector • Applied data mining techniques to identify the customer having high likelihood of churn in prepaid service base • Analysed, Explored and Prepared data –identified outliers, missing values and treated them and used the cleaned data for predictive data modelling techniques • Started with 578 variables; reduced variables based on univariate analysis, low variance, multicollinearity and applied feature selection. • By Iterative modeling process and business understanding finally 11 predictors were selected • Various models were implemented using Python (Logistic Regression, Decision Tree, Naïve Bayes, Ensemble Methods) • Validated the different models developed using various evaluation metrics • Compared all the models developed and selected the best one • The best model was Gradient Boosting having an accuracy of 92%, misclassification rate of 8%, cumulative lift of 5.75, KS of 58.64 and ROC of 91%. • Profiled customers using K-Means Clustering to design best service program specific to customers’ segments
Time Series Analysis of Agricultural Production (Food Grains) in India
April 1, 2016 – Present
• To predict the production of various food grains such as rice, wheat, coarse cereals, and pulses using time series models. • We have collected the production data from 1950 to 2014 from RBI database. • We used single variant time series analysis for our study. • The time series forecasting of the production of each food grains based on previously observed values was calculated. • Autoregressive Integrated Moving Average Model (ARIMA), model was the best fit.
Customer Churn Management Program
March 1, 2016 – Present
• To develop a statistical model for predicting customer churn and use the model to identify the most important drivers of churn. • Did initial data pre-processing and cleaning of a dataset containing 71,047 records and 78 variables. • Built a model, using Logistic Regression, Random Forest and Artificial Neural Networks, which delineates the key factors that lead to customer churn. Model was trained using a calibration dataset of 40,000 records. • Predictive accuracy of our final model came to be around 69%.
Assessing the impact of mobile advertisement amongst consumers
March 1, 2016 – Present
• To find out how individuals attitude towards shopping are correlated with mobile marketing. • To check the reliability of mobile marketing. • Conducted focus groups, interviews to perform initial exploratory research. • Prepared a questionnaire to conduct a survey. • Tested different hypotheses from the data obtained and analysed the factors responsible using Logistic Regression.
Analysis of the factors affecting Housing Prices
February 1, 2016 – Present
• Determining various factors affecting Housing Prices. • Data was collected for 546 observations of sales price of houses in the city of Windsor in Ontario, Canada for the year 1987. • Multiple regression was carried out on secondary data to find out relationships between the housing prices and independent factors such as lot size, number of bedrooms, number of bathrooms, central air conditioning etc. • Formulated models depicting the effects of these factors.
Smart Transportation System
September 1, 2014 – June 1, 2015
• Designed a car to autonomously navigate through a track by detecting lanes and centering itself between them as well as detect objects in front of it and avoid collision.
What is Data Science?
IBM
June 25, 2026 – Present
Fraud Detection in Python
DataCamp
June 25, 2026 – Present
Visualizing Time Series Data in Python
DataCamp
June 25, 2026 – Present
Machine Learning for Time Series Data in Python
DataCamp
June 25, 2026 – Present
Data Science Methodology
IBM
June 25, 2026 – Present
Ask Questions to Make Data-Driven Decisions
June 25, 2026 – Present
Introduction to Data Science Specialization
IBM
June 25, 2026 – Present
Introduction to Network Analysis in Python
DataCamp
June 25, 2026 – Present
Introduction to SQL
DataCamp
June 25, 2026 – Present
Tools for Data Science
IBM
June 25, 2026 – Present
Introduction to R
DataCamp
June 25, 2026 – Present
AI For Everyone
DeepLearning.AI
June 25, 2026 – Present
Essentials of MLOps with Azure: 3 Spark MLflow Projects on Databricks
June 25, 2026 – Present
Essentials of MLOps with Azure: 1 Introduction
June 25, 2026 – Present
The Employee's Guide to Sustainability
June 25, 2026 – Present
Prepare Data for Exploration
June 25, 2026 – Present
How Google does Machine Learning
Google Cloud
June 25, 2026 – Present
Applied Text Mining in Python
University of Michigan
June 25, 2026 – Present
Digital Transformation
Boston Consulting Group (BCG)
June 25, 2026 – Present
Data Visualization with Python
IBM
June 25, 2026 – Present
Understanding and Visualizing Data with Python
University of Michigan
June 25, 2026 – Present
Data Frameworks for Generative AI
Fractal Analytics
June 25, 2026 – Present
Essentials of MLOps with Azure: 2 Databricks MLflow and MLflow Tracking
June 25, 2026 – Present
Introduction to Machine Learning in Production
Coursera
June 25, 2026 – Present
Foundations: Data, Data, Everywhere
June 25, 2026 – Present
Introduction to Git and GitHub
June 25, 2026 – Present
Intermediate Network Analysis in Python
DataCamp
June 25, 2026 – Present
Perform Sentiment Analysis with scikit-learn
Coursera
June 25, 2026 – Present
Intro to Time Series Analysis in R
Coursera
June 25, 2026 – Present
Practical Time Series Analysis
The State University of New York
June 25, 2026 – Present
Generative AI Essentials: A Comprehensive Introduction
Fractal Analytics
June 25, 2026 – Present
Using Databases with Python
University of Michigan
June 25, 2026 – Present
Develop Generative AI Applications: Get Started
IBM
June 25, 2026 – Present
MLOps Essentials: Model Development and Integration
June 25, 2026 – Present
What Is Generative AI?
June 25, 2026 – Present
Foundations of Project Management
June 25, 2026 – Present
Analyze Data to Answer Questions
June 25, 2026 – Present
Introduction to Portfolio Risk Management in Python
DataCamp
June 25, 2026 – Present
Applied Machine Learning in Python
University of Michigan
June 25, 2026 – Present
Databases and SQL for Data Science
IBM
June 25, 2026 – Present
Cultural Fit Analysis
The candidate's diverse project portfolio, ranging from customer churn prediction to time series analysis and even a smart transportation system, indicates a broad interest and adaptability. Experience across multiple companies (ALDAR, Swvl, Anheuser-Busch InBev, Ericsson, CoreCompete) and roles (Senior Associate, Product Data Scientist, Mentor) suggests an ability to integrate into different organizational cultures. The focus on practical, problem-solving projects aligns well with a results-oriented environment. The numerous certifications, including those in Generative AI and MLOps, demonstrate a commitment to continuous learning and staying current with industry trends.
Soft Skills & Operational Fit
The candidate's experience as a Data Science Mentor and involvement in placement activities at IIT Kanpur suggest strong communication, leadership, and stakeholder management skills. The project descriptions indicate an ability to translate business requirements into technical solutions and work with diverse teams. The certifications in project management and MLOps also point to an understanding of operational aspects of data science projects.