Urvin, data scientist

Urvin

Senior Data Scientist (Marketing Science)

Cairo, Egypt · UTC+2 (Africa/Cairo) · 3 years of experience

Urvin focuses on turning messy data into tested models and useful decisions.

Request a shortlist

Why this profile fits

Decision-first problem framing

Starts with the decision, target metric, and data limits before choosing a model or analytical method.

Validated modeling

Uses holdouts, experiment design, and error analysis to separate a useful signal from a convincing notebook.

Clear operational handoff

Documents assumptions, monitoring needs, and the path from analysis to a decision or production workflow.

Relevant toolkit

PythonSQLscikit-learnPyTorchdbt

Delivery evidence

Selected work

Bayesian Marketing Mix Model

Consumer goods brand (MENA)

Built a Bayesian marketing mix model in PyMC with adstock and diminishing-returns saturation curves to attribute revenue across 6 paid channels and 40 SKUs. Delivered channel-level ROI and response curves that guided quarterly budget reallocation and cut attribution error from 22% to 9%.

PythonPyMC

Price Elasticity & Promotion Optimizer

E-commerce marketplace

Estimated own-price and cross-price elasticities using log-log regression and hierarchical models on two years of transaction data. The resulting promotion optimizer recommended discount depths per category and reduced margin erosion on promoted SKUs by an estimated 8%.

Pythonstatsmodels
View more profile detail →

Relevant experience

Career timeline

Data Scientist (Marketing Science)

Sep 2024–Present

Devlyn Client Engagements (Remote Bench) · Remote (Cairo, Egypt)

  • Delivered marketing mix and price elasticity models for consumer goods and e-commerce clients, cutting spend-attribution error from 22% to 9% on the flagship FMCG engagement.

Senior Software Engineer

May 2025–Present

ViitorCloud Technologies · Ahmedabad, Gujarat, India

  • Estimated own-price and cross-price elasticities on two years of transaction data, informing category discount depths that protected margin during peak-sale events.

Software Engineer

Jan 2023–Jul 2025

ViitorCloud Technologies · Ahmedabad, Gujarat, India

  • Wrote SQL and pandas pipelines to consolidate campaign, sales, and survey data for 8 consumer brands into a single analysis-ready dataset.

Skill depth

Show experience in context.

VerbalCommunicationDomainUnderstandingProblemSolvingCodeQualitySystemDesignDeliverySpeed
Competency shapeAssessment across the same six dimensions used for every profile.

Relevant experience by skill

Python3 years
SQL3 years
pandas3 years
scikit-learn3 years
Marketing Mix Modeling2 years
statsmodels2 years
dbt2 years
Streamlit2 years
See the complete skill index

Languages

PythonSQLRBash

Frameworks

scikit-learnPyMCPyTorchTensorFlowStreamlitdbtProphet

Libraries/APIs

pandasPolarsNumPystatsmodelsSciPyLightGBMXGBoostMatplotlibseabornPlotlyLangChain

Tools

GitMLflowJupyterDockerAirflowGreat ExpectationsGitHub Actions

Paradigms

Bayesian InferenceA/B TestingCausal InferenceTime-Series ForecastingFeature EngineeringMLOps

Platforms

SnowflakeBigQueryGoogle CloudAWS SageMaker

Storage

PostgreSQLpgvectorBigQueryAmazon RedshiftParquet

Other

Marketing Mix ModelingPrice ElasticityAdstock & Saturation ModelingUplift ModelingGoogle Analytics 4

Education

Formal background

BSc, Statistics (minor in Computer Science)

Cairo University · 2018–2022 · Graduated with honors, GPA 3.6/4.0

Credentials

Certifications

AWS Certified Machine Learning Engineer – Associate

Amazon Web Services · 2023 · Certified

Communication

Languages

Arabic

Native

English

Fluent

French

Conversational

More examples

Similar Data Scientist profiles.