Prudhvi Teja Cherukuri

Data Scientist

Hyderabad, IN.

About

Highly analytical Data Scientist with over two years of experience leveraging advanced marketing analytics and machine learning solutions to drive significant business results. Expertise includes customer segmentation, uplift modeling, and causal inference, consistently cultivating data-driven frameworks that enhance marketing effectiveness. Proven track record of developing innovative predictive models that promote substantial GMV growth for leading clients.

Work

Blend360

|

Data Scientist

Hyderabad, Telangana, India

→

Summary

Led advanced marketing analytics initiatives for Walmart, leveraging machine learning to drive significant business results and incremental GMV growth.

Highlights

Developed propensity and uplift models (Metalearner/ITE) to identify high-value households for targeted direct mail campaigns, driving $22.2M in incremental GMV.

Designed and executed causal inference and synthetic control approaches to accurately measure campaign lift and retention impact for multi-channel strategies.

Evaluated causal impact of direct mail catalogs using response and GMV models, achieving over 80% accuracy in predicting incremental spending and purchase probability.

Built robust Python/SQL pipelines for transaction-level data processing, feature engineering, and model scoring, enhancing data-backed decision-making.

Delivered 15+ advanced analytics projects for Walmart, covering campaign measurement, customer segmentation, incrementality modeling, and retention analysis.

Blend360

|

Associate Data Scientist

Hyderabad, Telangana, India

→

Summary

Developed an end-to-end NLP solution for customer feedback analysis, enhancing sentiment and entity extraction across hospitality and retail sectors.

Highlights

Built an end-to-end NLP solution to analyze large-scale customer reviews across hospitality and retail, utilizing FLAIR, Stanza, and VADER for entity extraction, clustering, and sentiment analysis.

Solved key NLP challenges, including cataphora resolution, over-clustering, and entity-level sentiment scoring, to improve analytical accuracy.

Education

Shiv Nadar University

Greater Noida, Uttar Pradesh, India
→
B. Tech Computer Science and Engineering

Skills

Languages and Tools

Python, SQL, PySpark, MS Excel, Streamlit.

Libraries/Frameworks

NumPy, Pandas, Scikit-Learn, Matplotlib, Linear Regression, Logistic Regression, Decision Trees, Random Forest, KNN, NLP, XGBoost, FLAIR, Stanza, VADER, Stable Diffusion, Dreambooth, LoRA (Low-Rank Adaptation), Marvin.

Analytics

Customer Segmentation, Synthetic Control, A/B Testing, Retention Analysis, Uplift Modeling, Causal Inference, Propensity Modeling.

Domains

Retail Analytics, Direct Mail Targeting, Marketing Campaign Measurement, Customer Feedback Analysis.

Projects

Bio Generator

→

Summary

Developed a system to generate customized professional bios using LLMs.

Personalized Image Creation

→

Summary

Designed and deployed a brand-personalized image generation system.